© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206293
    Prev
    Next
    INDEX
    Explanations

    skills, interests, and passions

    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_20_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
     IN
    0.42
    цкий
    0.39
     faith
    0.39
     قول
    0.38
    ENSIVE
    0.38
     люби
    0.37
     $\
    0.36
    喈
    0.36
     હે
    0.36
     INTO
    0.36
    POSITIVE LOGITS
    would
    0.40
    median
    0.40
    ndon
    0.38
    dw
    0.37
    bg
    0.37
    wd
    0.37
    bf
    0.36
    dW
    0.36
    λει
    0.36
    rees
    0.36
    Activations Density 0.006%

    No Known Activations