© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33216
    Prev
    Next
    INDEX
    Explanations

    brooke St

    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_31_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
    닿
    0.32
     kN
    0.32
    🔁
    0.31
     Factories
    0.30
    geordnet
    0.29
    タミン
    0.29
    銷售
    0.29
    サイクル
    0.29
     हिंदु
    0.28
     অ্যাসিড
    0.28
    POSITIVE LOGITS
     études
    0.37
    研究
    0.36
    azza
    0.33
     housed
    0.32
    Despatx
    0.31
    ONES
    0.31
     изуча
    0.31
    㞓
    0.31
    âtel
    0.30
    的研究
    0.30
    Activations Density 0.001%

    No Known Activations