© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196133
    Prev
    Next
    INDEX
    Explanations

    return home

    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_15_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
     dolor
    0.23
    보다
    0.23
     weakly
    0.23
     चलाने
    0.23
    ってきた
    0.22
    棕
    0.22
     则
    0.22
    
    0.22
     मा
    0.22
     ไม
    0.22
    POSITIVE LOGITS
     be
    0.25
    arap
    0.24
    owym
    0.24
    BQ
    0.24
    egas
    0.24
    beis
    0.24
    VW
    0.23
    oslash
    0.23
    RBI
    0.23
    Rp
    0.23
    Activations Density 0.003%

    No Known Activations