© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46431
    Prev
    Next
    INDEX
    Explanations

    statsmodels

    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_3_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
     Statue
    0.99
     стату
    0.90
     Statute
    0.82
     statute
    0.73
     verificación
    0.73
     statue
    0.71
    <0x80>
    0.70
    Statuses
    0.70
    िंग्स
    0.70
    getStatus
    0.70
    POSITIVE LOGITS
    d
    1.26
    ra
    1.08
    g
    0.93
    w
    0.86
    )
    0.84
    র
    0.83
    r
    0.81
    x
    0.80
    Q
    0.78
     is
    0.77
    Activations Density 0.001%

    No Known Activations