© 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. 33918
    Prev
    Next
    INDEX
    Explanations

    Sunday school, roast, best, Tzu

    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
    t
    0.79
    in
    0.76
    。「
    0.59
    td
    0.58
     disrupt
    0.54
     urm
    0.53
     t
    0.53
    ts
    0.52
    ेलर
    0.52
     дослід
    0.52
    POSITIVE LOGITS
    2
    0.78
    ING
    0.76
     ambigu
    0.71
    нд
    0.71
    পান
    0.68
    quakes
    0.65
    ς
    0.65
     obliquely
    0.64
    ри
    0.63
    ಶಾ
    0.62
    Activations Density 0.001%

    No Known Activations