© 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. 80476
    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
     pisos
    0.42
     புத்தக
    0.37
     óptica
    0.37
    Readable
    0.37
    읽
    0.36
    Кли
    0.36
    ')"
    0.36
     موجوده
    0.36
     livros
    0.36
    理工
    0.36
    POSITIVE LOGITS
     شاہ
    0.38
     стре
    0.38
    measure
    0.37
     stress
    0.37
    '$
    0.36
     টাক
    0.36
     Stress
    0.36
     Indiana
    0.35
     प्रकारे
    0.35
     death
    0.35
    Activations Density 0.000%

    No Known Activations