© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18523
    Prev
    Next
    INDEX
    Explanations

    look no further

    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_34_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
     foment
    0.38
     inciting
    0.38
     вз
    0.38
    зик
    0.37
     Melanie
    0.37
    criptors
    0.37
     `:`,
    0.36
    漉
    0.36
    价比
    0.36
     смысле
    0.36
    POSITIVE LOGITS
     друго
    0.37
     경우
    0.35
     ಏಕೆಂದರೆ
    0.35
     stranger
    0.35
    ұ
    0.35
    דים
    0.34
    <>
    0.34
     کیونکہ
    0.34
     波
    0.34
     到
    0.33
    Activations Density 0.001%

    No Known Activations