© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62240
    Prev
    Next
    INDEX
    Explanations

    workmate

    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_11_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
    t
    0.77
     .
    0.59
    ll
    0.57
    classe
    0.57
    ller
    0.55
    llas
    0.55
     Reduced
    0.54
    tl
    0.54
     Allowing
    0.53
    y
    0.53
    POSITIVE LOGITS
     vym
    0.55
     použí
    0.54
     pravidel
    0.53
     функцию
    0.52
     metri
    0.51
     ставки
    0.51
     functie
    0.51
     функция
    0.51
     composants
    0.51
     generan
    0.49
    Activations Density 0.001%

    No Known Activations