© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134352
    Prev
    Next
    INDEX
    Explanations

    microbial

    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_1_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
    ل
    1.52
    it
    1.25
    im
    1.25
    ح
    1.23
    <0x0D>
    1.18
    ال
    1.16
    los
    1.11
    com
    1.10
     имена
    1.10
    ivne
    1.09
    POSITIVE LOGITS
    は
    1.20
     في
    0.97
     preclude
    0.91
    ;
    0.91
    는
    0.91
     जिसकी
    0.87
    ۔
    0.87
     foothold
    0.86
     paragraphe
    0.86
    是
    0.86
    Activations Density 0.000%

    No Known Activations