© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137896
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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_46_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
     परसेंट
    0.45
    percentage
    0.44
    %",
    0.44
    %";
    0.43
    ennies
    0.43
     \%$
    0.43
    %+
    0.42
    Percentage
    0.42
    "%
    0.41
     percentage
    0.41
    POSITIVE LOGITS
     Quốc
    0.41
     rafts
    0.38
     Salim
    0.38
     Frog
    0.37
     excluir
    0.37
     ट्रू
    0.37
    蔥
    0.37
     Chip
    0.36
     rooster
    0.36
    स्वर
    0.36
    Activations Density 0.001%

    No Known Activations