© 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. 45544
    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
     punctu
    0.57
     punctuated
    0.56
     coinciding
    0.52
     Terima
    0.50
     welchem
    0.50
    Җ
    0.50
    jee
    0.48
     bienvenidas
    0.48
     coincided
    0.48
     kidding
    0.47
    POSITIVE LOGITS
    er
    0.67
    ার
    0.55
    вались
    0.55
    ו
    0.55
    ine
    0.54
    orm
    0.54
    인
    0.54
     be
    0.53
    ly
    0.53
    лов
    0.52
    Activations Density 0.000%

    No Known Activations