© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26436
    Prev
    Next
    INDEX
    Explanations

    c# configuration files

    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_10_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
    ли
    0.64
    א
    0.60
    تر
    0.59
    ν
    0.58
    ち
    0.57
    তি
    0.56
     on
    0.55
    D
    0.55
    $
    0.55
     emphasised
    0.54
    POSITIVE LOGITS
    h
    0.62
     這個
    0.56
    ześnie
    0.56
     politiques
    0.55
    y
    0.52
     כמו
    0.51
     আরা
    0.51
    ahlen
    0.49
     विरोधी
    0.49
     Dreaming
    0.49
    Activations Density 0.018%

    No Known Activations