© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210364
    Prev
    Next
    INDEX
    Explanations

    acting or needed medications

    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_20_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
    aleza
    0.51
    仕組み
    0.46
    kind
    0.45
    ₁,
    0.44
     bulun
    0.44
    Elim
    0.43
    বিধ
    0.42
     பொருந்த
    0.42
    elim
    0.40
    LK
    0.40
    POSITIVE LOGITS
     Frankreich
    0.44
     intracellular
    0.41
    TransactionLog
    0.41
    䣫
    0.41
    မ်
    0.41
    ार्क
    0.41
    బ్ద
    0.41
    ประกาศ
    0.40
     බොහෝ
    0.39
     invertebrate
    0.39
    Activations Density 0.001%

    No Known Activations