© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205335
    Prev
    Next
    INDEX
    Explanations

    aezakmi, aethoria, praesidium

    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_6_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
    ell
    0.90
    Y
    0.90
    اس
    0.88
    LE
    0.87
    iksa
    0.87
    ΙΚ
    0.87
    Κ
    0.87
    وس
    0.85
    Z
    0.84
    کز
    0.84
    POSITIVE LOGITS
    с
    1.34
     (
    1.29
    a
    1.22
    ться
    1.13
    на
    0.95
     .
    0.95
    в
    0.95
     detract
    0.93
     к
    0.90
    <0xF3>
    0.89
    Activations Density 0.001%

    No Known Activations