© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92455
    Prev
    Next
    INDEX
    Explanations

    caret

    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_60_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
    ^^
    0.54
    osk
    0.46
    ^^^^
    0.43
    டோ
    0.42
    :\
    0.40
    os
    0.39
    ঁপ
    0.39
    ട്ടില്‍
    0.39
    :</
    0.39
    :")
    0.38
    POSITIVE LOGITS
    出
    1.33
    出て
    1.16
    出会
    1.15
    出演
    1.14
    บริการ
    1.12
    出して
    1.12
    か
    1.12
    向
    1.10
    出した
    1.09
    かけて
    1.06
    Activations Density 0.002%

    No Known Activations