© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170321
    Prev
    Next
    INDEX
    Explanations

    never, ever

    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
    Negative Logits
     O
    0.46
    ote
    0.45
     Dy
    0.44
    菟
    0.44
     Style
    0.43
    ne
    0.42
     trovato
    0.42
     Dw
    0.42
    |}
    0.41
    na
    0.41
    POSITIVE LOGITS
    Stable
    0.50
    Kiza
    0.47
    чна
    0.45
    VIDED
    0.43
    േഷ്
    0.43
    Gul
    0.42
    Sale
    0.42
    Leading
    0.41
    рая
    0.41
    ESD
    0.41
    Activations Density 0.001%

    No Known Activations