© 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. 129761
    Prev
    Next
    INDEX
    Explanations

    commands and mentions

    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
    ל
    1.34
    ون
    1.30
    ON
    1.29
    та
    1.16
    م
    1.13
    ک
    1.12
     be
    1.08
    نا
    1.08
    м
    1.04
     as
    1.02
    POSITIVE LOGITS
    s
    1.02
    은
    0.72
    r
    0.69
    리의
    0.67
    re
    0.66
    aval
    0.66
    ’
    0.66
    는
    0.66
    కు
    0.66
    이었다
    0.66
    Activations Density 0.000%

    No Known Activations