© 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. 10957
    Prev
    Next
    INDEX
    Explanations

    mentions of "et al", typically used in citations

    oai_token-act-pair · gemini-2.0-flash

    al

    np_max-act · gemini-2.0-flash

    ▁al

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     BoxDecoration
    -0.90
     فريبيس
    -0.87
    fjspx
    -0.86
     commissioner
    -0.84
    ConstraintMaker
    -0.83
     nakalista
    -0.82
     Процитовано
    -0.81
    MigrationBuilder
    -0.81
    AccessorTable
    -0.79
    Искәрмәләр
    -0.78
    POSITIVE LOGITS
    <bos>
    0.66
    '
    0.47
    Cyril
    0.40
    Haupt
    0.40
    joi
    0.39
     Ehren
    0.39
    nting
    0.39
    krati
    0.39
     Munic
    0.39
    float
    0.38
    Activations Density 0.729%

    No Known Activations