© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220700
    Prev
    Next
    INDEX
    Explanations

    too quickly or soon

    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_10_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
    ités
    0.49
    кой
    0.48
    <0xBE>
    0.47
    é
    0.47
    从
    0.46
    𝐞
    0.46
    <0xBF>
    0.44
    ens
    0.44
    ا
    0.44
    ang
    0.44
    POSITIVE LOGITS
    0.68
     ד
    0.49
     ສ
    0.45
     তিনি
    0.45
     not
    0.44
     only
    0.44
    </h2>
    0.44
     offre
    0.44
     ব
    0.44
     guzt
    0.43
    Activations Density 0.007%

    No Known Activations