© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163617
    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_13_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
     erred
    0.55
     явления
    0.51
     앞으로
    0.51
     스타일
    0.51
     Эр
    0.51
    patx
    0.50
     фонда
    0.50
     프
    0.49
    ொண்ட
    0.49
     짜
    0.48
    POSITIVE LOGITS
    c
    0.58
    ò
    0.54
    ils
    0.49
     împ
    0.48
    î
    0.48
    ar
    0.48
    ch
    0.47
    O
    0.47
    HV
    0.46
    DIY
    0.46
    Activations Density 0.000%

    No Known Activations