© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159026
    Prev
    Next
    INDEX
    Explanations

    IHME, Böhmer, Dahmer, Khmer

    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_2_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
    ução
    1.26
    ции
    1.21
     représentation
    1.16
    ución
    1.16
    다
    1.13
     oposición
    1.12
    ể
    1.11
    ătur
    1.11
     dirección
    1.10
    cción
    1.09
    POSITIVE LOGITS
    s
    1.70
    स
    1.54
     in
    1.52
    f
    1.50
    .
    1.48
    m
    1.46
    ס
    1.43
    G
    1.42
     the
    1.40
    מ
    1.35
    Activations Density 0.000%

    No Known Activations