© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15345
    Prev
    Next
    INDEX
    Explanations

    words that start with apostrophes, single digit numbers, words "de", "le", "la", "une", "un", and common french pronouns

    oai_token-act-pair · gemini-2.0-flash

    words with archaic spelling or formal tone

    np_token-act-pair-logits · gpt-4o-mini

    single quote

    np_max-act-logits · gemini-2.0-flash

    '

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STRUCTIONS
    -0.80
    Londres
    -0.76
    Còn
    -0.74
    olished
    -0.73
     per
    -0.73
    bacher
    -0.73
     V
    -0.72
     v
    -0.72
     w
    -0.72
    Numerade
    -0.71
    POSITIVE LOGITS
     itſelf
    1.21
     myſelf
    1.05
     occaf
    1.04
     uſ
    1.01
     greateſt
    1.01
     Majefty
    0.96
     unſ
    0.94
     themſelves
    0.91
     inſ
    0.91
     uſe
    0.91
    Activations Density 0.862%

    No Known Activations