© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166727
    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_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
    Bast
    0.37
     vegetative
    0.37
    ణ
    0.37
    Verified
    0.36
    resol
    0.36
     passport
    0.36
     detectar
    0.35
    zo
    0.35
     спу
    0.35
    unshift
    0.34
    POSITIVE LOGITS
     Donne
    0.41
     Strange
    0.40
    平时
    0.40
    妳
    0.38
     Gone
    0.38
    奇异
    0.38
    懟
    0.37
     অদ্ভুত
    0.37
     treated
    0.37
     विचित्र
    0.37
    Activations Density 0.000%

    No Known Activations