© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10196
    Prev
    Next
    INDEX
    Explanations

    PHP code

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     تضيفلها
    -0.56
    nesty
    -0.43
    ourable
    -0.40
    ʁ
    -0.39
    iliary
    -0.37
     Abbott
    -0.36
    直
    -0.36
    "}")
    -0.35
     thing
    -0.35
    ssy
    -0.35
    POSITIVE LOGITS
     themſelves
    0.73
    seamnă
    0.72
     Efq
    0.71
     itſelf
    0.68
     SEDS
    0.65
     Majefty
    0.65
     ſever
    0.64
     Reſ
    0.64
     greateſt
    0.64
     oamen
    0.63
    Activations Density 14.374%

    No Known Activations