© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68362
    Prev
    Next
    INDEX
    Explanations

    say honey

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     البط
    0.43
    Special
    0.43
    addSql
    0.40
     أب
    0.39
     اب
    0.38
    𒄩
    0.38
    數位
    0.37
    ╗
    0.37
     Slov
    0.37
     Special
    0.36
    POSITIVE LOGITS
     local
    0.67
     locally
    0.59
    local
    0.56
     स्थानीय
    0.50
     lokalen
    0.49
    当地
    0.49
     lokal
    0.47
     местного
    0.47
     lokale
    0.46
    locally
    0.46
    Activations Density 0.005%

    No Known Activations