© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13767
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to software code and statistical demographics

    oai_token-act-pair · gemini-2.0-flash

    Code generation and results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Jefus
    -0.76
     Efq
    -0.69
    <bos>
    -0.68
    ContentLoaded
    -0.67
     оригіналу
    -0.67
     Monfieur
    -0.66
     defStyle
    -0.65
    hånd
    -0.63
     entanto
    -0.62
     poussière
    -0.62
    POSITIVE LOGITS
    Biographie
    0.47
     hier
    0.47
     mej
    0.43
    WRENCE
    0.42
    secta
    0.41
    foy
    0.41
    மை
    0.40
     elegans
    0.40
    ToPoint
    0.40
    充分
    0.40
    Activations Density 1.372%

    No Known Activations