© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40688
    Prev
    Next
    INDEX
    Explanations

    tip-of-the-hat gesture, cringey, gauntlet, longevity

    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_11_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
    s
    0.61
    다
    0.57
     or
    0.57
    r
    0.57
    스
    0.55
     the
    0.53
    m
    0.53
    or
    0.52
    ing
    0.51
    ม
    0.51
    POSITIVE LOGITS
    <unused1072>
    0.53
     तैयारियां
    0.49
     моз
    0.49
    <unused302>
    0.49
    𝟮
    0.48
     товар
    0.48
    рованный
    0.48
     воспроиз
    0.47
     προϊ
    0.47
    abhave
    0.46
    Activations Density 0.000%

    No Known Activations