© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11341
    Prev
    Next
    INDEX
    Explanations

    language related to legal contracts and judgements.

    oai_token-act-pair · gemini-2.0-flash

    legal contracts and agreements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    XmlAccessType
    -0.43
    beta
    -0.38
    elsa
    -0.37
    writeField
    -0.36
    вича
    -0.36
    Delta
    -0.35
    FieldError
    -0.35
     beta
    -0.35
     alumínio
    -0.35
     Luft
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.93
    tvguidetime
    0.89
    Personensuche
    0.87
     Paglinawan
    0.85
     الاطلاع
    0.85
     myſelf
    0.85
    Autoritní
    0.84
     nakalista
    0.84
     Monfieur
    0.84
    ConstraintMaker
    0.81
    Activations Density 4.354%

    No Known Activations