© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141844
    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_0_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
    _
    0.74
    {
    0.67
    an
    0.67
    鶘
    0.63
    시
    0.62
    $.
    0.61
     on
    0.59
    اف
    0.59
     for
    0.58
     byen
    0.58
    POSITIVE LOGITS
    y
    0.66
     disturbs
    0.58
    ών
    0.57
     coher
    0.57
    s
    0.57
     mezzanine
    0.55
     Ι
    0.54
    ів
    0.54
    ের
    0.53
     in
    0.52
    Activations Density 0.000%

    No Known Activations