© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83251
    Prev
    Next
    INDEX
    Explanations

    verbose mode

    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
    י
    1.59
    ни
    1.56
    ي
    1.28
     distinguer
    1.27
     khăn
    1.24
     россия
    1.24
     tourne
    1.24
    𝘪
    1.20
     Павел
    1.19
    i
    1.19
    POSITIVE LOGITS
    ly
    1.63
    高
    1.56
    тся
    1.52
    ad
    1.43
    কে
    1.41
    ap
    1.35
    지
    1.35
     (
    1.31
    ett
    1.30
    يا
    1.28
    Activations Density 0.000%

    No Known Activations