© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199194
    Prev
    Next
    INDEX
    Explanations

    tethered, untethered

    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_9_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
    ном
    0.97
     дан
    0.93
    示す
    0.88
     što
    0.86
    ές
    0.86
    ᱤ
    0.86
     jūs
    0.84
    ۰
    0.84
    ной
    0.84
    ೋಗ್ಯ
    0.84
    POSITIVE LOGITS
    us
    1.80
    on
    1.62
    in
    1.51
    os
    1.48
    et
    1.45
    u
    1.43
    S
    1.42
    ت
    1.37
    as
    1.36
    D
    1.36
    Activations Density 0.000%

    No Known Activations