© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3088
    Prev
    Next
    INDEX
    Explanations

    mentions of a medical study, procedures and outcomes, or a presentation of medical case results.

    oai_token-act-pair · gemini-2.0-flash

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     '\\;'
    -0.77
    enterOuterAlt
    -0.77
    SharedCtor
    -0.73
     Drapeau
    -0.71
    aarrggbb
    -0.70
    migrationBuilder
    -0.70
     <>",
    -0.69
    RegressionTest
    -0.68
    expandindo
    -0.68
     متعلقه
    -0.66
    POSITIVE LOGITS
     useful
    0.46
    ~
    0.43
     guinea
    0.42
     frustrated
    0.42
    ommation
    0.40
    Virt
    0.37
    ~(
    0.37
    J
    0.37
    ～、
    0.36
    ئه
    0.36
    Activations Density 1.758%

    No Known Activations