© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240511
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     گیم
    0.52
     بازیکن
    0.51
     chuột
    0.50
     ذکر
    0.46
    <unused938>
    0.46
    ANGMAR
    0.45
    絟
    0.45
     corroborated
    0.45
     ಮುಂದೆ
    0.44
    <unused983>
    0.44
    POSITIVE LOGITS
     o
    0.49
    Be
    0.48
    1
    0.47
    甭
    0.46
    ي
    0.46
    Sa
    0.45
     that
    0.44
     syllables
    0.44
    bees
    0.44
    be
    0.44
    Activations Density 0.000%

    No Known Activations