© 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. 76534
    Prev
    Next
    INDEX
    Explanations

    complications and errors

    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
     Mao
    0.42
     elective
    0.39
    毛
    0.39
     cos
    0.37
     毛
    0.37
     sun
    0.36
     cont
    0.36
     vitamin
    0.35
     vitamins
    0.35
     menging
    0.35
    POSITIVE LOGITS
     ERROR
    0.41
     verre
    0.39
     erreurs
    0.38
     ValueError
    0.38
    澼
    0.38
     errori
    0.38
    呱
    0.38
    лав
    0.37
    ERROR
    0.37
     reten
    0.37
    Activations Density 0.001%

    No Known Activations