© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218351
    Prev
    Next
    INDEX
    Explanations

    language end punctuation

    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_31_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
     which
    0.44
     które
    0.43
    鉅
    0.38
     которые
    0.38
     koje
    0.38
    ينية
    0.37
    ord
    0.37
    delim
    0.36
     $\{
    0.36
     še
    0.36
    POSITIVE LOGITS
    abbas
    0.42
     resorted
    0.39
     whip
    0.38
     eff
    0.36
     effluent
    0.35
    )…
    0.35
     foaming
    0.34
     resort
    0.34
     whipped
    0.34
    ότερα
    0.33
    Activations Density 0.000%

    No Known Activations