© 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. 7884
    Prev
    Next
    INDEX
    Explanations

    legal jargon and language used in court proceedings

    oai_token-act-pair · gemini-2.0-flash

    legal terms and concepts

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

    Legal/accusation contexts

    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
     محفوظة
    -0.54
    حياتها
    -0.46
     Réponses
    -0.45
    مش
    -0.44
    FIND
    -0.43
    GeoNames
    -0.43
    TextBoxColumn
    -0.43
    find
    -0.42
    LAHOMA
    -0.42
    annte
    -0.41
    POSITIVE LOGITS
    
    0.94
    UnusedPrivate
    0.76
     TestBed
    0.67
    aarrggbb
    0.65
    HCC
    0.62
     heapq
    0.60
    intention
    0.58
     intentionally
    0.57
    putExtra
    0.55
     knowingly
    0.55
    Activations Density 6.064%

    No Known Activations