© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50061
    Prev
    Next
    INDEX
    Explanations

    regions or areas

    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_30_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
    症状
    0.42
    镖
    0.41
     Evidently
    0.36
     அறிகுற
    0.35
     конди
    0.34
     শতাধিক
    0.34
     अभिकथन
    0.34
     cylinders
    0.33
     Consequences
    0.33
     ખાતે
    0.33
    POSITIVE LOGITS
    lax
    0.40
     ప్రభుత్వం
    0.40
     정부
    0.40
     복
    0.39
    }-${
    0.39
     lake
    0.39
     രാഷ്ട്ര
    0.38
     government
    0.38
     iyo
    0.38
     отриму
    0.38
    Activations Density 0.009%

    No Known Activations