© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46104
    Prev
    Next
    INDEX
    Explanations

    `[Range(float, float)]` or `Range` parameters

    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_22_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
    ماء
    0.47
    Р
    0.46
    EEP
    0.45
     indicated
    0.43
    Optimal
    0.42
     bodies
    0.41
     optimal
    0.41
    Pair
    0.40
    挿
    0.40
    Macrophages
    0.40
    POSITIVE LOGITS
     मुगल
    0.49
    adillo
    0.45
     сложные
    0.43
     રાજ
    0.43
    <0x00>
    0.42
     Turing
    0.42
    écie
    0.41
    ánto
    0.41
     නමුත්
    0.41
    anga
    0.40
    Activations Density 0.000%

    No Known Activations