© 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. 15370
    Prev
    Next
    INDEX
    Explanations

    code syntax, sometimes including variable names and array names

    oai_token-act-pair · gemini-2.0-flash

    unusual or archaic words

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

    Javascript 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_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
    Negative Logits
     
    -1.20
     [
    -1.05
     (
    -1.05
     V
    -0.98
     B
    -0.97
     I
    -0.96
    <eos>
    -0.95
     R
    -0.93
     A
    -0.93
     de
    -0.92
    POSITIVE LOGITS
     myſelf
    1.98
     Theſe
    1.98
     itſelf
    1.97
     Monfieur
    1.84
     raiſ
    1.79
     uſed
    1.67
    expandindo
    1.67
     faſt
    1.66
     متعلقه
    1.65
     houſe
    1.63
    Activations Density 2.853%

    No Known Activations