© 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. 6043
    Prev
    Next
    INDEX
    Explanations

    phrases related to the progression of game related athletic events

    oai_token-act-pair · gemini-2.0-flash

    go

    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
    يميديا
    -0.58
    \{\\
    -0.55
    SENS
    -0.53
     فريبيس
    -0.53
    Obrázky
    -0.53
    Revenir
    -0.51
     Sist
    -0.50
    lité
    -0.49
     Shiba
    -0.49
     traveled
    -0.48
    POSITIVE LOGITS
    Попис
    0.70
    addCriterion
    0.68
    contentLoaded
    0.59
     EconPapers
    0.59
    richTextPanel
    0.58
    bcryptjs
    0.57
     TextAppearance
    0.54
     légales
    0.53
    migrationBuilder
    0.52
    XmlAccessorType
    0.52
    Activations Density 0.272%

    No Known Activations