© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32316
    Prev
    Next
    INDEX
    Explanations

    Linear Algebra

    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_7_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
     psychotherapy
    0.75
     dermatology
    0.75
    I
    0.73
    {//
    0.70
     arrhythmias
    0.69
     করিয়৷
    0.69
    $...
    0.68
     immunotherapy
    0.67
     ސ
    0.66
     분포
    0.66
    POSITIVE LOGITS
    at
    1.38
    ad
    1.34
    n
    1.22
    as
    1.19
    on
    1.18
    id
    1.02
    x
    1.01
    is
    1.00
    r
    0.98
    et
    0.98
    Activations Density 0.002%

    No Known Activations