© 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. 36242
    Prev
    Next
    INDEX
    Explanations

    correct answer is

    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
    ן
    0.61
     Gile
    0.59
     बचे
    0.56
     Lala
    0.55
     веке
    0.53
    lair
    0.52
     savaş
    0.52
    玝
    0.51
     tộc
    0.50
    นิ
    0.50
    POSITIVE LOGITS
    (
    0.67
    3
    0.59
    4
    0.56
    +
    0.54
    (“
    0.53
    2
    0.53
    ct
    0.52
    mol
    0.52
    [
    0.52
    oc
    0.51
    Activations Density 0.006%

    No Known Activations