© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246942
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     евре
    0.38
    虢
    0.37
     אין
    0.37
     تحفظ
    0.36
     äl
    0.36
     லி
    0.36
    marginY
    0.36
     संरक्षित
    0.35
    密封
    0.35
    柺
    0.35
    POSITIVE LOGITS
    0.40
    зья
    0.39
    apt
    0.38
     कर्ण
    0.38
     laughing
    0.37
     accidentally
    0.37
    ATCH
    0.37
     posta
    0.37
     laughs
    0.37
    pow
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.