© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53907
    Prev
    Next
    INDEX
    Explanations

    strong or weak

    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
    懵
    0.46
     beck
    0.42
     আসে
    0.39
    geois
    0.38
    चारियों
    0.38
     бекер
    0.38
     Pasal
    0.37
     Buz
    0.37
     ಯೋಜ
    0.37
    勹
    0.36
    POSITIVE LOGITS
    ajer
    0.37
    学科
    0.37
    પ્
    0.36
    ELO
    0.36
    ◯
    0.34
    NO
    0.34
    Prevent
    0.34
     ве
    0.34
    aud
    0.34
    [*
    0.34
    Activations Density 0.002%

    No Known Activations