© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207908
    Prev
    Next
    INDEX
    Explanations

    call something name or title

    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_20_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
     constant
    0.44
    銚
    0.42
     accident
    0.41
     ample
    0.41
    ذة
    0.40
    initial
    0.40
     Casualty
    0.40
    آ
    0.40
     sărb
    0.40
     wales
    0.40
    POSITIVE LOGITS
    hatian
    0.44
     ресурс
    0.43
     تعلم
    0.42
     sited
    0.40
    女神
    0.40
     అభివృద్ధి
    0.39
     mengembangkan
    0.38
     Диа
    0.38
    㪕
    0.38
    reek
    0.38
    Activations Density 0.000%

    No Known Activations