© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15107
    Prev
    Next
    INDEX
    Explanations

    words related to law, finance, or legal procedures.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "active"

    np_token-act-pair-logits · gpt-4o-mini

    active

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ########.
    -0.74
    OGND
    -0.73
    клопе
    -0.71
     مشين
    -0.66
    AccessorTable
    -0.63
    PreExecute
    -0.60
    basicConfig
    -0.58
    HtmlAttribute
    -0.56
    parseDouble
    -0.56
    Assured
    -0.56
    POSITIVE LOGITS
     active
    2.27
    active
    1.94
    Active
    1.86
     Active
    1.84
     ACTIVE
    1.70
    ACTIVE
    1.62
     activo
    1.54
     actif
    1.53
     aktif
    1.52
     aktive
    1.49
    Activations Density 2.893%

    No Known Activations