© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198395
    Prev
    Next
    INDEX
    Explanations

    crossed out or marked text

    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_15_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
     he
    0.55
     yada
    0.50
     was
    0.48
     لگانا
    0.48
    ísmo
    0.48
    듐
    0.48
     tn
    0.47
     här
    0.46
     monomial
    0.46
    ಋ
    0.46
    POSITIVE LOGITS
     Автор
    0.54
    】,
    0.52
    Автор
    0.50
    Dalam
    0.49
    Dentro
    0.48
    น้อง
    0.47
    an
    0.46
     工作
    0.46
    できて
    0.46
     pigmentation
    0.46
    Activations Density 0.001%

    No Known Activations