© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219242
    Prev
    Next
    INDEX
    Explanations

    produced by

    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_31_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
     scarves
    0.38
     ор
    0.37
     ores
    0.35
     mơ
    0.35
    elling
    0.35
    Economics
    0.34
    消
    0.34
    輯
    0.34
     $@
    0.34
     படங்கள்
    0.33
    POSITIVE LOGITS
     ایف
    0.42
     அமைந்துள்ள
    0.39
     Oficina
    0.38
     oficina
    0.38
    也都
    0.38
     dedicating
    0.38
     Dip
    0.36
     Taille
    0.36
    实验室
    0.35
     निष्क्रिय
    0.35
    Activations Density 0.001%

    No Known Activations