© 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. 86692
    Prev
    Next
    INDEX
    Explanations

    hundred to thousand/million

    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
    ية
    1.53
    t
    1.16
    \
    1.03
     to
    1.00
     be
    0.87
    人
    0.87
    した
    0.85
    ある
    0.80
    dehyde
    0.80
    ال
    0.78
    POSITIVE LOGITS
    u
    0.86
    ς
    0.82
    اهای
    0.71
    Ranges
    0.69
    i
    0.66
    fov
    0.66
    aplan
    0.65
    are
    0.64
    aat
    0.64
    assigned
    0.63
    Activations Density 0.000%

    No Known Activations