© 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. 6504
    Prev
    Next
    INDEX
    Explanations

    Words and phrases for surface damage and/or degradation.

    oai_token-act-pair · gemini-2.0-flash

    corrosion and oxidation

    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
     SPDX
    -0.56
    ransition
    -0.53
    autorest
    -0.51
    rxjs
    -0.50
    kew
    -0.50
    errHandler
    -0.50
     Theil
    -0.50
    nocache
    -0.47
     OnEnable
    -0.45
     Salve
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.65
    parsedMessage
    0.62
    NOPQRST
    0.56
     Мексичка
    0.55
     Generals
    0.53
    thâu
    0.52
    VersionUID
    0.51
     Wikimedijinoj
    0.50
    migrationBuilder
    0.50
    LookAnd
    0.50
    Activations Density 2.263%

    No Known Activations