© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80995
    Prev
    Next
    INDEX
    Explanations

    | separator

    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
    ↵↵
    1.53
     a
    1.47
     that
    1.34
    า
    1.32
    that
    1.13
    ี
    1.13
    ü
    1.09
    a
    1.05
     on
    1.04
    а
    1.02
    POSITIVE LOGITS
    assapi
    1.11
    I
    1.10
    cosim
    1.09
    dbjc
    1.04
     résident
    1.03
    n
    1.03
    و
    1.02
    nico
    1.01
    elwv
    1.01
     конец
    1.00
    Activations Density 0.000%

    No Known Activations