© 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. 36656
    Prev
    Next
    INDEX
    Explanations

    alliance, field, stages, law

    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
     compartil
    0.64
     sadde
    0.56
    काळ
    0.55
     khel
    0.52
    o
    0.52
    𝑭
    0.52
     kalem
    0.51
     Sadd
    0.50
     Sedan
    0.50
    सद
    0.49
    POSITIVE LOGITS
     بالإضافة
    0.47
     ї
    0.45
    utz
    0.43
    isyon
    0.42
    间的
    0.40
    撸
    0.39
     જ્યાં
    0.39
    with
    0.38
     цу
    0.38
    uten
    0.38
    Activations Density 0.011%

    No Known Activations