© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130782
    Prev
    Next
    INDEX
    Explanations

    be a

    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_25_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
     wad
    0.26
     insulate
    0.26
    iodate
    0.25
     particulière
    0.25
     comme
    0.25
     Dated
    0.24
     Chest
    0.23
    及
    0.23
     comté
    0.23
    aule
    0.23
    POSITIVE LOGITS
    similar
    0.31
     მს
    0.30
     similar
    0.29
     valores
    0.29
    valores
    0.28
     mirip
    0.27
     utiliza
    0.26
    Similar
    0.25
     adapta
    0.25
    imilar
    0.25
    Activations Density 0.020%

    No Known Activations