© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10846
    Prev
    Next
    INDEX
    Explanations

    capturar, capacidad, en serio

    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_40_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
     સ્વા
    0.42
    raphics
    0.40
    न्त्र
    0.40
     $€
    0.39
    Evening
    0.38
     waffle
    0.37
     taff
    0.37
    🧇
    0.37
    owości
    0.36
    inoza
    0.36
    POSITIVE LOGITS
     EEC
    0.38
    πον
    0.38
    ZC
    0.37
     estimation
    0.36
     estimations
    0.36
     eco
    0.35
     estimate
    0.35
    作
    0.34
     Conduit
    0.33
    ඕ
    0.33
    Activations Density 0.058%

    No Known Activations