© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106378
    Prev
    Next
    INDEX
    Explanations

    development

    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_1_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
    ing
    1.52
    ა
    1.20
    il
    1.12
    I
    1.12
    E
    1.10
    ä
    1.01
    Z
    0.99
    T
    0.96
    ти
    0.94
    ow
    0.91
    POSITIVE LOGITS
    to
    1.45
     to
    1.39
    ي
    1.16
    i
    1.16
     was
    1.11
     is
    1.08
    ان
    1.04
     akan
    1.01
    め
    0.95
    де
    0.93
    Activations Density 0.001%

    No Known Activations