© 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. 83369
    Prev
    Next
    INDEX
    Explanations

    circumcision

    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
    .
    2.17
    ید
    1.93
    دی
    1.63
    ED
    1.56
    OR
    1.42
    IN
    1.39
    فی
    1.34
    ,
    1.31
    ds
    1.30
     juggling
    1.30
    POSITIVE LOGITS
    يلي
    1.70
     以
    1.55
    يء
    1.52
    天
    1.48
    水
    1.48
    ？
    1.47
    一
    1.46
     يك
    1.44
    一些
    1.42
     اين
    1.42
    Activations Density 0.000%

    No Known Activations