© 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. 217869
    Prev
    Next
    INDEX
    Explanations

    socket and connection logic

    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
     ->
    0.36
     bijective
    0.34
     northbound
    0.34
    呼吸
    0.33
     podrán
    0.33
     maybe
    0.33
     mogą
    0.31
     __
    0.31
     Mohr
    0.30
    的人
    0.30
    POSITIVE LOGITS
    PDA
    0.40
    Nos
    0.35
    Gestion
    0.35
    PF
    0.33
    ifts
    0.32
    डा
    0.32
    MF
    0.32
    支援
    0.32
    並
    0.32
    BF
    0.32
    Activations Density 0.006%

    No Known Activations