© 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-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175587
    Prev
    Next
    INDEX
    Explanations

    defining jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stdout
    0.46
    Token
    0.46
     комбина
    0.45
    Abbreviations
    0.45
    Localization
    0.45
    酺
    0.43
     پیدا
    0.43
    Shock
    0.43
    箕
    0.43
    椑
    0.43
    POSITIVE LOGITS
     vaid
    0.53
    gegevens
    0.50
     hice
    0.48
    į
    0.47
    lge
    0.44
     varios
    0.43
    their
    0.43
     brillant
    0.43
     cost
    0.43
     avait
    0.43
    Activations Density 0.009%

    No Known Activations