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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13961
    Prev
    Next
    INDEX
    Explanations

    court documents and associated terminology

    oai_token-act-pair · gemini-2.0-flash

    legalistic language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Theſe
    -0.92
     myſelf
    -0.81
     itſelf
    -0.80
    %"),
    -0.78
    ->__
    -0.77
    __':
    -0.77
     ''),
    -0.77
    TypedDataSet
    -0.76
     []),
    -0.76
    __':
    -0.75
    POSITIVE LOGITS
     (
    0.54
    getOut
    0.50
    </b>
    0.48
     Pacífico
    0.48
     Audiodateien
    0.48
    ​
    0.47
     A
    0.47
    !
    0.46
    </u>
    0.44
    ,
    0.43
    Activations Density 3.147%

    No Known Activations