© 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. 1927
    Prev
    Next
    INDEX
    Explanations

    single digit numbers, ordinal numbers and words related to the passage of time.

    oai_token-act-pair · gemini-2.0-flash

    phrases that start with 'e', 'A', 'I', or 'S'

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

    general english text

    np_max-act-logits · gemini-2.0-flash
    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
     myſelf
    -1.59
    expandindo
    -1.52
     itſelf
    -1.48
     ſeveral
    -1.42
     Monfieur
    -1.37
     pleaſure
    -1.35
     Efq
    -1.30
     Jefus
    -1.29
     ſtate
    -1.28
     iſt
    -1.27
    POSITIVE LOGITS
     ever
    0.94
     A
    0.66
    ,
    0.66
     e
    0.65
     I
    0.65
     
    0.64
     u
    0.64
     S
    0.61
     t
    0.60
     i
    0.60
    Activations Density 1.595%

    No Known Activations