© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209279
    Prev
    Next
    INDEX
    Explanations

    monthly, quarterly, end of period

    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_25_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
    髹
    0.30
     nyil
    0.29
    <unused277>
    0.29
     ஆகியவை
    0.27
    侵
    0.27
     manifeste
    0.27
     Dated
    0.27
    swire
    0.27
    Ꮮ
    0.27
    iat
    0.27
    POSITIVE LOGITS
     parked
    0.33
     desert
    0.31
     pre
    0.30
     दरबार
    0.30
    毎回
    0.30
     accur
    0.29
     consistently
    0.29
     metal
    0.29
     hitched
    0.29
     conditioner
    0.29
    Activations Density 0.001%

    No Known Activations