© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214378
    Prev
    Next
    INDEX
    Explanations

    PlayStation Network

    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_5_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
     an
    1.28
    ↵↵
    1.17
    ↵
    1.13
     a
    1.09
     o
    1.07
    お金
    1.03
     ample
    1.00
     sayıda
    0.99
     (
    0.96
     l
    0.95
    POSITIVE LOGITS
    ي
    2.05
    i
    1.78
    ad
    1.63
    us
    1.60
    m
    1.53
    ق
    1.45
    ul
    1.41
    b
    1.40
    ம்
    1.35
    ie
    1.33
    Activations Density 0.003%

    No Known Activations