© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46520
    Prev
    Next
    INDEX
    Explanations

    ACL, EMNLP, NAACL

    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_3_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
    N
    1.00
    ك
    0.97
    '
    0.86
    U
    0.84
    (
    0.84
    {
    0.82
    B
    0.82
    ب
    0.82
    W
    0.80
    “
    0.78
    POSITIVE LOGITS
    ן
    0.66
    ীয়
    0.65
    ையில்
    0.65
    ین
    0.60
     hydrating
    0.59
    ālā
    0.59
    ște
    0.58
     attham
    0.58
     yattha
    0.58
    ione
    0.58
    Activations Density 0.003%

    No Known Activations