© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58939
    Prev
    Next
    INDEX
    Explanations

    end

    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_59_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
    {
    0.83
    {-
    0.64
    {\
    0.64
    {.
    0.62
    {:
    0.61
    {*
    0.60
    {}\
    0.58
    {})
    0.57
    {}{
    0.57
    {"
    0.55
    POSITIVE LOGITS
     Ries
    0.36
    he
    0.35
    不出
    0.34
    нің
    0.34
    Deck
    0.34
    वह
    0.34
     Localization
    0.34
     عين
    0.33
    V
    0.33
    Lip
    0.33
    Activations Density 0.000%

    No Known Activations