© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13582
    Prev
    Next
    INDEX
    Explanations

    code snippets, variable names, and programming-related acronyms

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    ⓧ
    -0.76
     שוליים
    -0.75
    aternion
    -0.75
    httphttps
    -0.74
    WriteBarrier
    -0.73
    CodeDom
    -0.71
    NamedQueries
    -0.71
    новниш
    -0.71
    /***/
    -0.70
     ProtoMessage
    -0.69
    POSITIVE LOGITS
     vana
    0.44
     lieve
    0.44
    取
    0.42
    っこう
    0.41
     lie
    0.41
    ollett
    0.41
    EnableWeb
    0.40
    写
    0.39
    พอ
    0.38
    report
    0.38
    Activations Density 1.727%

    No Known Activations