© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194172
    Prev
    Next
    INDEX
    Explanations

    binocular vision

    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_4_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
    i
    0.19
     for
    0.18
    e
    0.18
    AN
    0.17
    he
    0.17
    ET
    0.16
    EL
    0.16
     jossa
    0.16
    IN
    0.16
    IT
    0.15
    POSITIVE LOGITS
    は
    0.20
    ли
    0.18
    しくは
    0.17
    ご
    0.17
    人
    0.17
    릉
    0.16
    кол
    0.16
    وتي
    0.16
    郎
    0.16
    у
    0.16
    Activations Density 0.002%

    No Known Activations