© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134128
    Prev
    Next
    INDEX
    Explanations

    unchained, unclean, untransformed, unclosed

    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_1_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
    u
    1.54
    К
    1.52
    ه
    1.30
    ي
    1.24
    й
    1.21
    いた
    1.20
    ی
    1.19
    И
    1.16
    Пе
    1.16
    Ш
    1.13
    POSITIVE LOGITS
    ong
    1.31
    <0x80>
    1.25
    em
    1.17
    ot
    1.13
    ia
    1.08
    och
    0.97
    ir
    0.95
    ant
    0.95
    um
    0.92
    cket
    0.90
    Activations Density 0.001%

    No Known Activations