© 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. 162515
    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
     Advisor
    0.41
     ferocious
    0.39
     MATH
    0.39
    高
    0.39
     राधा
    0.37
    曷
    0.37
     sépt
    0.37
    ܡ
    0.37
    ತ್ರ
    0.37
    毂
    0.36
    POSITIVE LOGITS
     konser
    0.43
    щини
    0.40
     decrement
    0.39
     konzerv
    0.39
     conserv
    0.39
    стане
    0.39
    电池
    0.38
    áni
    0.38
     conservación
    0.37
    ដាក់
    0.37
    Activations Density 0.000%

    No Known Activations