© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87302
    Prev
    Next
    INDEX
    Explanations

    fan out

    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_23_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
    ẏ
    0.47
     հետ
    0.45
     bialgebras
    0.42
     einzige
    0.40
    ँचा
    0.40
    ळ्यात
    0.39
     forhold
    0.39
     eneste
    0.38
    畞
    0.38
    绺
    0.38
    POSITIVE LOGITS
     Around
    0.50
     Mult
    0.46
     multip
    0.45
     حول
    0.45
     MULT
    0.44
     multidis
    0.44
     around
    0.43
     mult
    0.41
     RAC
    0.40
     alrededor
    0.39
    Activations Density 0.024%

    No Known Activations