© 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. 142647
    Prev
    Next
    INDEX
    Explanations

    URLs and domains

    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
     ঠিক
    0.38
     жок
    0.38
    %';
    0.38
     содержи
    0.37
    ']>;
    0.37
    Ago
    0.36
    Hind
    0.36
    Burst
    0.36
    罄
    0.36
    絊
    0.36
    POSITIVE LOGITS
     Edin
    0.44
     RSD
    0.44
    (),"
    0.42
     ede
    0.41
     ed
    0.38
     EDL
    0.38
     羽
    0.37
     dataType
    0.36
     EDC
    0.36
     Lander
    0.36
    Activations Density 0.013%

    No Known Activations