© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13617
    Prev
    Next
    INDEX
    Explanations

    language related to legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    Related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    aarrggbb
    -0.61
     indisponible
    -0.56
    olingo
    -0.53
    hwar
    -0.51
    asin
    -0.50
    ző
    -0.49
    ToScroll
    -0.49
    ymce
    -0.48
    retz
    -0.48
     gyhoeddwyd
    -0.47
    POSITIVE LOGITS
     related
    2.38
     Related
    2.14
    related
    2.02
    Related
    1.88
     RELATED
    1.73
     associated
    1.30
    associated
    1.22
     connected
    1.16
     relacionado
    1.13
    相关的
    1.11
    Activations Density 6.179%

    No Known Activations