© 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. 220788
    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
     சினிம
    0.40
    .;
    0.39
     statistique
    0.38
     définir
    0.37
    어도
    0.37
     estadísticas
    0.37
     Estadística
    0.36
    няется
    0.36
    汇报
    0.36
    सुबह
    0.36
    POSITIVE LOGITS
     breathed
    0.38
     __(
    0.37
     gor
    0.36
     tocc
    0.34
     center
    0.34
     Bentham
    0.34
     Simplified
    0.32
     Gor
    0.32
    cas
    0.31
     O
    0.31
    Activations Density 0.000%

    No Known Activations