© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6445
    Prev
    Next
    INDEX
    Explanations

    strings of author names, years, and publication information

    oai_token-act-pair · gemini-2.0-flash

    citation/bibliography

    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
     ModelExpression
    -0.73
     Pingback
    -0.72
     itſelf
    -0.68
     שוליים
    -0.63
     estekak
    -0.61
    findpost
    -0.59
     vhs
    -0.58
     Cæsar
    -0.58
     Anſ
    -0.57
    COUVER
    -0.57
    POSITIVE LOGITS
    "](
    0.53
    ชั่น
    0.47
     ánimo
    0.45
    nteral
    0.44
    encie
    0.44
    Compli
    0.44
    iffe
    0.43
    Fprintf
    0.43
    webElement
    0.42
    locke
    0.42
    Activations Density 0.958%

    No Known Activations