© 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. 89592
    Prev
    Next
    INDEX
    Explanations

    (generally, hopefully, unfortunately, often)

    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
    砖
    0.46
     coluna
    0.42
     plains
    0.40
    <>());
    0.40
     verticals
    0.39
     lineup
    0.38
     kutoka
    0.38
     nominated
    0.38
    នៃ
    0.38
    >>,
    0.38
    POSITIVE LOGITS
     ρ
    0.44
     پن
    0.42
     الأمر
    0.40
    ensors
    0.39
     コード
    0.38
     لدى
    0.38
     هل
    0.38
     በፊት
    0.38
     vermeiden
    0.38
     অ্যাল
    0.37
    Activations Density 0.001%

    No Known Activations