© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218729
    Prev
    Next
    INDEX
    Explanations

    request/response structures

    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_31_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
    凱
    0.37
     نح
    0.37
     fox
    0.35
    ण्या
    0.35
     Graph
    0.34
     cinerea
    0.33
     Term
    0.33
    ﾒ
    0.33
     DR
    0.33
    xE
    0.33
    POSITIVE LOGITS
     fim
    0.40
    닮
    0.40
    ＝＝
    0.39
     prist
    0.38
    ستی
    0.37
    fim
    0.37
    toxicity
    0.36
     peered
    0.36
    時間が
    0.36
     вибра
    0.36
    Activations Density 0.000%

    No Known Activations