© 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. 131947
    Prev
    Next
    INDEX
    Explanations

    adjustments

    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
     ομά
    1.25
     arabe
    1.21
     esperienza
    1.18
    và
    1.18
     interno
    1.17
    tahun
    1.16
    어
    1.15
     evento
    1.14
    ために
    1.14
    जा
    1.13
    POSITIVE LOGITS
    (
    1.16
    ↵↵
    1.13
    3
    1.12
     to
    0.99
     as
    0.90
    al
    0.89
    izes
    0.89
    s
    0.86
    2
    0.85
    6
    0.85
    Activations Density 0.001%

    No Known Activations