© 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. 247053
    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
    Wrapper
    0.41
    sig
    0.40
     Пен
    0.40
    Guesses
    0.40
    ぐ
    0.38
    acc
    0.37
     \"
    0.37
    امات
    0.36
    commercial
    0.36
     commerciali
    0.36
    POSITIVE LOGITS
     স্থাপ
    0.44
    кы
    0.39
     MCA
    0.38
     pelatihan
    0.38
     differential
    0.38
     Bf
    0.38
     zonal
    0.37
     allocates
    0.37
     CRM
    0.36
    🦯
    0.36
    Activations Density 0.001%

    No Known Activations