© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13776
    Prev
    Next
    INDEX
    Explanations

    words related to legal liability, damage, and responsibility

    oai_token-act-pair · gemini-2.0-flash

    legal / technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     rootReducer
    -0.42
     cauldron
    -0.41
     drummer
    -0.38
    locene
    -0.38
     spiders
    -0.37
     ricotta
    -0.34
     Pozna
    -0.34
     Zapo
    -0.33
    peed
    -0.33
     Mic
    -0.33
    POSITIVE LOGITS
     <=",
    0.80
    elemField
    0.76
     समीक्षक
    0.69
    tagHelperRunner
    0.68
    ⓧ
    0.68
    XmlType
    0.66
    FTFY
    0.66
    $_['
    0.64
     Obligation
    0.64
     Administrativna
    0.63
    Activations Density 32.724%

    No Known Activations