© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83787
    Prev
    Next
    INDEX
    Explanations

    lore

    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_0_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
     في
    1.34
    ین
    1.25
    ূপে
    1.24
    もら
    1.23
    ো
    1.16
    籶
    1.16
    ва
    1.15
     در
    1.13
     وګټ
    1.13
    Ǘ
    1.13
    POSITIVE LOGITS
    a
    2.16
    i
    1.84
    च
    1.76
    ب
    1.69
    ه
    1.68
    se
    1.66
    ?
    1.63
    !
    1.60
    ored
    1.56
    هم
    1.56
    Activations Density 0.001%

    No Known Activations