© 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. 104036
    Prev
    Next
    INDEX
    Explanations

    Ramses VI Tomb, Scream VI, Ares VI

    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
    dır
    1.22
    l
    1.13
    t
    1.12
    d
    1.12
    ა
    1.03
    in
    1.02
    もら
    0.99
    ل
    0.95
    ים
    0.94
    dirs
    0.91
    POSITIVE LOGITS
    _
    1.34
    :
    1.03
    .
    0.96
    '
    0.89
    O
    0.87
    4
    0.87
    um
    0.84
    ?
    0.82
    F
    0.82
    ow
    0.81
    Activations Density 0.000%

    No Known Activations