© 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. 59196
    Prev
    Next
    INDEX
    Explanations

    hot topic

    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
    ânea
    0.29
    ⼈
    0.29
     समय
    0.28
    "){
    0.28
    uosa
    0.26
    Time
    0.25
    ")],
    0.25
    wała
    0.25
     месте
    0.25
    énez
    0.25
    POSITIVE LOGITS
     (
    0.26
    !!
    0.26
     Episode
    0.25
    !
    0.24
     egész
    0.24
     Verbesserung
    0.24
     સત
    0.23
     அப்படி
    0.22
     تاسو
    0.22
     κάτι
    0.22
    Activations Density 0.011%

    No Known Activations