© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 195987
    Prev
    Next
    INDEX
    Explanations

    dynamic languages, dependency, remarkable generation, generations model, considerations, triacylglycerols, continuous, deviates

    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_26_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
     in
    0.33
    E
    0.31
    eee
    0.30
    D
    0.30
     imaginary
    0.30
    도
    0.30
    在
    0.30
    لم
    0.29
    Part
    0.29
    .
    0.29
    POSITIVE LOGITS
     思っ
    0.37
     Decreto
    0.33
    стые
    0.32
     razão
    0.31
    բ
    0.30
     Belanda
    0.30
    aunque
    0.30
    भावस्था
    0.30
     seguidores
    0.29
    getStartState
    0.29
    Activations Density 0.000%

    No Known Activations