© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36539
    Prev
    Next
    INDEX
    Explanations

    Espressif Systems

    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_3_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
    '
    0.97
    t
    0.96
    K
    0.92
    dad
    0.85
    li
    0.84
    V
    0.84
    deki
    0.79
    F
    0.78
    ت
    0.78
    ED
    0.75
    POSITIVE LOGITS
    ка
    0.97
     about
    0.96
     a
    0.87
     as
    0.87
     by
    0.87
    ive
    0.83
     về
    0.83
    ۰
    0.80
     tentang
    0.79
     who
    0.78
    Activations Density 0.001%

    No Known Activations