© 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. 165463
    Prev
    Next
    INDEX
    Explanations

    foreign words or phrases

    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
    identity
    0.39
     ഓൺലൈ
    0.38
     emotions
    0.36
    شا
    0.35
    完
    0.35
    soort
    0.35
    يق
    0.34
     instead
    0.34
    窓
    0.34
    勉強
    0.33
    POSITIVE LOGITS
    ாரம்
    0.43
    ^*\
    0.41
     திறன்
    0.40
     unterstüt
    0.40
     Bick
    0.40
     ट्रेस
    0.40
     Elektrokhimiya
    0.39
     Unterstützung
    0.37
    谆
    0.36
     ड्रिल
    0.36
    Activations Density 0.000%

    No Known Activations