© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20163
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     ){
    0.42
    niają
    0.42
     {
    0.40
     ”,
    0.39
    ruiter
    0.37
    iculation
    0.37
    tsk
    0.37
     ！
    0.36
    ధీ
    0.36
     ।”
    0.35
    POSITIVE LOGITS
     {"
    0.51
    ({'
    0.45
    ({"
    0.44
    
    0.44
    ${\
    0.43
    {"
    0.42
    ‫
    0.39
    
    0.39
     [{'
    0.38
     ${\
    0.38
    Activations Density 0.004%

    No Known Activations