© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85005
    Prev
    Next
    INDEX
    Explanations

    space manifold geometric variety

    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_23_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
    ба
    0.33
     отзы
    0.32
     Regal
    0.32
    representative
    0.32
    润
    0.32
    Привет
    0.31
     toning
    0.31
     tones
    0.31
    $.}
    0.31
    ிற்க
    0.30
    POSITIVE LOGITS
     नुकसान
    0.33
    がありました
    0.32
    もあります
    0.32
     มุม
    0.32
    があります
    0.31
    嗇
    0.31
     fosse
    0.30
    splitter
    0.30
    शुल्क
    0.30
     sly
    0.29
    Activations Density 0.001%

    No Known Activations