© 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. 211590
    Prev
    Next
    INDEX
    Explanations

    superhero names followed by punctuation

    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
     प्रोत्साहन
    0.47
     MUST
    0.46
     Heaven
    0.45
     Norwegen
    0.44
    ]])
    0.43
    ]]
    0.43
     Edinburgh
    0.43
     INVEST
    0.43
     Save
    0.42
     Invest
    0.42
    POSITIVE LOGITS
     amikor
    0.46
    𝑪
    0.45
    軾
    0.44
    Ⴀ
    0.43
    ʁ
    0.42
     aquare
    0.42
    TypeArguments
    0.42
     rheumatic
    0.41
     метр
    0.41
    പ്പെട്ട്
    0.41
    Activations Density 0.001%

    No Known Activations