© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48417
    Prev
    Next
    INDEX
    Explanations

    Ch

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     featuring
    0.40
    .??
    0.39
     Featuring
    0.38
    揭
    0.37
     fetching
    0.37
    use
    0.35
    播出
    0.35
    🐍
    0.35
    ંગી
    0.34
    .;
    0.34
    POSITIVE LOGITS
     Francesco
    0.43
    carbam
    0.42
     Fag
    0.41
     Caro
    0.41
    car
    0.40
    carbox
    0.40
     Carmine
    0.40
    brackets
    0.40
    htra
    0.39
    사회
    0.39
    Activations Density 0.001%

    No Known Activations