© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84333
    Prev
    Next
    INDEX
    Explanations

    avg or fab

    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_0_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
    人
    1.49
    Password
    1.41
    وا
    1.37
    Text
    1.30
    ست
    1.30
    Message
    1.27
    Status
    1.23
    Email
    1.23
    Name
    1.15
    Time
    1.15
    POSITIVE LOGITS
    larni
    1.74
    する
    1.46
    지
    1.43
    र
    1.41
    ल
    1.33
    цию
    1.30
    лиги
    1.28
    ми
    1.27
    이었
    1.27
    н
    1.27
    Activations Density 0.000%

    No Known Activations