© 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. 140394
    Prev
    Next
    INDEX
    Explanations

    weight definitions and comparisons

    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
     t
    0.56
    ur
    0.56
     înc
    0.55
     îl
    0.54
    リ
    0.54
    ਿਸ
    0.54
     که
    0.53
    loft
    0.53
    伝え
    0.52
     سعید
    0.52
    POSITIVE LOGITS
    H
    0.47
    LaunchAction
    0.46
    本日
    0.46
    UNE
    0.46
    尣
    0.45
    ாண
    0.45
     několika
    0.45
     الأش
    0.45
    дная
    0.44
    ASTM
    0.44
    Activations Density 0.002%

    No Known Activations