© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217953
    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_16_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
    as
    0.54
    or
    0.54
    at
    0.53
    and
    0.52
    TS
    0.52
    on
    0.52
    ed
    0.51
    2
    0.51
    ATS
    0.51
    ast
    0.50
    POSITIVE LOGITS
     искусство
    0.65
     отвер
    0.61
     ecuaciones
    0.60
    ईआरटी
    0.58
     impuestos
    0.56
     vincul
    0.56
     vehement
    0.55
     нарушения
    0.55
     нарушение
    0.55
     искусства
    0.54
    Activations Density 0.000%

    No Known Activations