© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31191
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     rum
    0.40
     tin
    0.39
    ีย
    0.36
    inz
    0.36
    ங
    0.36
     چې
    0.35
     ਕਿ
    0.34
     cellspacing
    0.34
     sk
    0.33
    ச்செய
    0.33
    POSITIVE LOGITS
    ♪
    0.38
    当局
    0.38
     Özellikle
    0.37
    ^)
    0.36
    ्यवाद
    0.36
     Após
    0.35
     (^
    0.35
     当然
    0.35
     ایسا
    0.35
     ありがとう
    0.35
    Activations Density 0.030%

    No Known Activations