© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38766
    Prev
    Next
    INDEX
    Explanations

    Asimov

    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_3_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
    ↵
    0.90
    of
    0.80
    </b>
    0.78
    </h2>
    0.73
    س
    0.72
    </h4>
    0.72
    </u>
    0.68
    </h1>
    0.64
    <0x0D>
    0.64
     têm
    0.62
    POSITIVE LOGITS
    ри
    0.68
    <0xBB>
    0.60
    ться
    0.60
    ский
    0.57
    acija
    0.57
    აში
    0.57
     Jordanian
    0.57
    க்குள்
    0.56
     spoonful
    0.56
    ri
    0.55
    Activations Density 0.000%

    No Known Activations