© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202490
    Prev
    Next
    INDEX
    Explanations

    ships, semi log, coupled plasma, tension leg platforms

    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_12_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
    g
    0.42
     vå
    0.42
     ను
    0.41
    üsseldorf
    0.41
    äs
    0.39
    arovski
    0.39
     जि
    0.39
    entropy
    0.39
    ப்படுகிறது
    0.38
    Ϩ
    0.38
    POSITIVE LOGITS
     swiftly
    0.45
     MCU
    0.45
     Modules
    0.45
     conclusively
    0.44
    も含
    0.44
    ATING
    0.43
    бил
    0.43
    чил
    0.43
     stack
    0.42
     कांस्टेबल
    0.42
    Activations Density 0.000%

    No Known Activations