© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15030
    Prev
    Next
    INDEX
    Explanations

    words in legal or forensic documents that refer to evidence or findings in a case

    oai_token-act-pair · gemini-2.0-flash

    Legal evidence

    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
    Демографія
    -0.69
    URLException
    -0.69
     برانيه
    -0.66
     esternos
    -0.66
    AutoScaleMode
    -0.63
    PerformLayout
    -0.63
    AndEndTag
    -0.61
    UrlResolution
    -0.59
    новниш
    -0.57
     autorytatywna
    -0.56
    POSITIVE LOGITS
     Directive
    0.48
     légale
    0.47
    ciuto
    0.45
     prati
    0.44
    ėjimo
    0.44
     pronouncing
    0.44
     bologna
    0.44
     Democrá
    0.44
     apo
    0.42
     legally
    0.42
    Activations Density 9.404%

    No Known Activations