© 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
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195553
    Prev
    Next
    INDEX
    Explanations

    squishy

    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_4_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
    ,
    1.15
    로
    0.89
    0.89
    們
    0.73
    લ
    0.72
    지는
    0.71
    вані
    0.70
     précie
    0.69
    ills
    0.68
    لے
    0.66
    POSITIVE LOGITS
    خ
    0.96
     by
    0.95
    el
    0.89
    ar
    0.88
    ра
    0.88
    in
    0.87
    an
    0.86
    ри
    0.84
    as
    0.84
    ਾ
    0.83
    Activations Density 0.002%

    No Known Activations