© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166717
    Prev
    Next
    INDEX
    Explanations

    code or math symbols }

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     LO
    0.46
     !}
    0.39
     ?)
    0.39
     crying
    0.36
     !)
    0.36
     ESP
    0.35
     cried
    0.34
    LO
    0.34
    spy
    0.34
    ()"
    0.33
    POSITIVE LOGITS
     {
    0.42
    {
    0.40
    {"
    0.39
    {'
    0.38
     {};
    0.36
    {(
    0.36
    ρη
    0.35
    ｛
    0.34
     நிக
    0.34
     {});
    0.33
    Activations Density 0.001%

    No Known Activations