© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143919
    Prev
    Next
    INDEX
    Explanations

    polish language requests

    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_0_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
    _
    1.50
    k
    1.47
     for
    1.41
     in
    1.30
    ’
    1.21
     constructors
    1.19
    anks
    1.17
    kannya
    1.16
    ri
    1.15
     accreditation
    1.15
    POSITIVE LOGITS
    ي
    2.16
    on
    1.95
    ين
    1.86
    ס
    1.81
    as
    1.65
    ض
    1.61
    ма
    1.59
    يق
    1.54
    يل
    1.52
    سي
    1.52
    Activations Density 0.001%

    No Known Activations