© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12002
    Prev
    Next
    INDEX
    Explanations

    explains "meaning"

    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_13_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
     SMTP
    0.33
     :',
    0.32
     S
    0.31
     :"
    0.30
     υ
    0.30
     Newspaper
    0.29
     VBA
    0.29
    u
    0.29
     ,
    0.29
     UTF
    0.29
    POSITIVE LOGITS
    kov
    0.28
    cube
    0.28
    ğim
    0.28
    ğe
    0.28
    약을
    0.28
    volve
    0.27
    ruce
    0.27
    agonia
    0.26
    kovi
    0.26
    ruitment
    0.26
    Activations Density 0.000%

    No Known Activations