© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245016
    Prev
    Next
    INDEX
    Explanations

    service name in docker contexts

    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_40_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
    &$\
    0.41
     //-
    0.41
    стная
    0.39
    Bet
    0.38
    嬰
    0.38
    LCD
    0.37
    BLACKLIST
    0.37
     Dois
    0.37
    στη
    0.36
    Todd
    0.36
    POSITIVE LOGITS
    singleton
    0.42
    ন্তন
    0.39
     emergent
    0.38
     singleton
    0.38
     castom
    0.37
    細
    0.36
    чески
    0.36
     যোগ্য
    0.35
     coverings
    0.35
     havent
    0.35
    Activations Density 0.001%

    No Known Activations