© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44000
    Prev
    Next
    INDEX
    Explanations

    output filename

    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_13_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
    اك
    0.18
    ك
    0.18
     oscillations
    0.17
     fiets
    0.17
     biographical
    0.17
     collapses
    0.17
     সিনে
    0.17
     marches
    0.16
     fits
    0.16
    陏
    0.16
    POSITIVE LOGITS
    ust
    0.21
    ॉय
    0.21
    ować
    0.21
    ată
    0.20
    Paradise
    0.19
    Of
    0.19
    Wifi
    0.19
    Charl
    0.18
    Equ
    0.18
    jekt
    0.18
    Activations Density 0.003%

    No Known Activations