© 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. 130064
    Prev
    Next
    INDEX
    Explanations

    synchronize

    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
    시
    0.98
     on
    0.95
    AS
    0.90
    体
    0.90
    から
    0.89
    ер
    0.86
    </strong>
    0.84
    B
    0.83
     quá
    0.82
     ofthe
    0.82
    POSITIVE LOGITS
    st
    1.06
    ati
    1.05
    bies
    0.94
    ma
    0.93
    ya
    0.93
    0
    0.93
    rov
    0.92
    pl
    0.89
    jene
    0.89
    ys
    0.88
    Activations Density 0.001%

    No Known Activations