© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13031
    Prev
    Next
    INDEX
    Explanations

    mentions of athletic championships

    oai_token-act-pair · gemini-2.0-flash

    World

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    yntaxException
    -0.73
    لينكات
    -0.72
    شهاد
    -0.71
     MainAxisSize
    -0.70
    expandindo
    -0.70
     whoſe
    -0.69
    Accessors
    -0.68
     mergeFrom
    -0.68
    enderror
    -0.67
     habet
    -0.67
    POSITIVE LOGITS
    UnknownFieldSet
    0.48
    Cursors
    0.40
    آخر
    0.36
    Eloquent
    0.36
     <=",
    0.36
     ch
    0.34
     sk
    0.34
     cura
    0.34
    uty
    0.33
    抜
    0.33
    Activations Density 0.804%

    No Known Activations