© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224293
    Prev
    Next
    INDEX
    Explanations

    in a / in the / in Gaza

    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_10_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
     Lalu
    0.72
    རྒྱ
    0.71
    in
    0.70
     Juga
    0.70
    すでに
    0.68
    お子
    0.68
    嶌
    0.68
     சேர்த்த
    0.66
     Dutta
    0.66
    できるよう
    0.65
    POSITIVE LOGITS
     stitches
    0.70
    ла
    0.68
    يث
    0.63
     amazement
    0.63
    _
    0.62
    ?
    0.62
    𝐠
    0.62
    рата
    0.61
     substrings
    0.61
    ून
    0.60
    Activations Density 0.034%

    No Known Activations