© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11043
    Prev
    Next
    INDEX
    Explanations

    a mix of words associated with auto-generation, management, and exceptions in code

    oai_token-act-pair · gemini-2.0-flash

    Log files and generated code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    NUMX
    -0.92
     المعيارى
    -0.82
     Wikispecies
    -0.77
    expandindo
    -0.71
    <bos>
    -0.68
     $_"
    -0.67
     ་་
    -0.67
    )";
    -0.66
     esternos
    -0.66
     disambiguazione
    -0.65
    POSITIVE LOGITS
    ه
    0.67
    er
    0.66
    rücken
    0.63
     each
    0.62
    ↵
    0.61
     rito
    0.59
    <unused63>
    0.59
     =
    0.58
     %
    0.58
     {
    0.57
    Activations Density 0.669%

    No Known Activations