© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78074
    Prev
    Next
    INDEX
    Explanations

    pres

    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_53_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
     pre
    0.45
     prem
    0.41
    嘱
    0.40
    ങ്ക
    0.38
    soup
    0.38
    pre
    0.37
    nestjs
    0.37
    Pre
    0.36
    Pres
    0.36
    ."'
    0.36
    POSITIVE LOGITS
    扈
    0.47
    ToBounds
    0.41
     வேண்டும்
    0.41
    犢
    0.39
     Cali
    0.39
    Xa
    0.39
     erfüllt
    0.38
    erView
    0.38
     स्त्र
    0.37
    acer
    0.37
    Activations Density 0.000%

    No Known Activations