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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11039
    Prev
    Next
    INDEX
    Explanations

    language related to delivering therapeutics

    oai_token-act-pair · gemini-2.0-flash

    scientific research and studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     concent
    -0.50
    migrationBuilder
    -0.49
     makl
    -0.47
    Diweddarwch
    -0.45
    談社
    -0.45
    ूरत
    -0.43
    aarrggbb
    -0.42
    enumi
    -0.42
     zr
    -0.42
    uesia
    -0.42
    POSITIVE LOGITS
     surla
    0.79
    PMailer
    0.67
     Gegenteil
    0.62
    endphp
    0.59
     lenker
    0.59
    rungsseite
    0.56
    omeness
    0.56
    piratory
    0.55
    ']?>
    0.55
    帖最后由
    0.54
    Activations Density 3.748%

    No Known Activations