© 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. 58864
    Prev
    Next
    INDEX
    Explanations

    behind and backs

    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
     پیچھے
    0.52
    D
    0.51
    G
    0.45
     الخلف
    0.44
    after
    0.43
    ኋላ
    0.42
    s
    0.41
    処分
    0.41
    F
    0.41
    ει
    0.40
    POSITIVE LOGITS
     has
    0.45
     kinase
    0.45
     is
    0.42
    liği
    0.42
    an
    0.41
    baş
    0.41
     પહેલા
    0.40
     and
    0.40
    nya
    0.40
     as
    0.40
    Activations Density 0.025%

    No Known Activations