© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58318
    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_2_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
    m
    0.93
    म
    0.91
    that
    0.88
    ri
    0.79
    this
    0.75
    p
    0.75
     that
    0.72
    ne
    0.69
    terer
    0.69
    ter
    0.69
    POSITIVE LOGITS
    O
    0.81
     މަ
    0.76
     as
    0.74
     or
    0.67
     страни
    0.65
     fabricación
    0.63
    инг
    0.63
    ٣
    0.63
    カイブ
    0.62
     comportamento
    0.62
    Activations Density 0.000%

    No Known Activations