© 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
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 3518
    Prev
    Next
    INDEX
    Explanations

    7

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     
    0.25
     no
    0.25
     upt
    0.23
     is
    0.23
     one
    0.23
     fire
    0.23
     up
    0.22
    Cho
    0.22
     "
    0.22
     every
    0.22
    POSITIVE LOGITS
     SalesLT
    0.30
     cendré
    0.28
    सदीय
    0.28
     plabic
    0.28
    𒂠
    0.28
     Apica
    0.27
     +#+
    0.27
    삵
    0.27
    <unused195>
    0.27
     RasterModelGrid
    0.27
    Activations Density 0.029%

    No Known Activations