© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140331
    Prev
    Next
    INDEX
    Explanations

    games, developers, or negative notoriety

    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_12_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
    skou
    0.57
    J
    0.54
    Auch
    0.52
     ALUMIN
    0.52
    aluminium
    0.51
     aluminium
    0.51
    !(
    0.49
    uruan
    0.49
    !
    0.48
    we
    0.48
    POSITIVE LOGITS
     pozitiv
    0.47
    خ
    0.47
    દ
    0.46
    股
    0.45
    知識
    0.45
     નિ
    0.42
     ре
    0.42
    なら
    0.42
    덱
    0.42
    財務
    0.42
    Activations Density 0.000%

    No Known Activations