© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3846
    Prev
    Next
    INDEX
    Explanations

    legal rulings and judgement concurrences within legal texts

    oai_token-act-pair · gemini-2.0-flash

    the word "concur" and its variations

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

    Legal context

    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
     AssemblyCulture
    -0.90
    ScopeManager
    -0.83
    Autoritní
    -0.75
    expandindo
    -0.75
    awtextra
    -0.71
    windowFixed
    -0.70
    SourceChecksum
    -0.70
    Personendaten
    -0.69
    migrationBuilder
    -0.69
    basicConfig
    -0.68
    POSITIVE LOGITS
    ring
    0.65
    ren
    0.60
    rs
    0.59
    r
    0.58
    ral
    0.57
    row
    0.57
    red
    0.54
    ret
    0.53
    rf
    0.52
    ry
    0.51
    Activations Density 1.615%

    No Known Activations