© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36989
    Prev
    Next
    INDEX
    Explanations

    het idee

    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
    i
    0.68
    fice
    0.67
    dSample
    0.63
    colare
    0.61
    aran
    0.60
     Hartree
    0.60
     تو
    0.59
    on
    0.59
    o
    0.59
    länder
    0.58
    POSITIVE LOGITS
    گ
    0.65
    詆
    0.57
    ชื่อ
    0.55
    ס
    0.53
     ochrony
    0.52
    স
    0.52
    اي
    0.51
     আহ্ব
    0.51
    ettes
    0.51
    וף
    0.51
    Activations Density 0.001%

    No Known Activations