© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153437
    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_23_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
     εν
    0.55
     алге
    0.54
    ťou
    0.53
    秵
    0.53
    érieure
    0.50
    ਕ
    0.50
     אל
    0.50
    阿拉
    0.49
     органі
    0.49
     ανθρώ
    0.49
    POSITIVE LOGITS
    ot
    0.66
    _
    0.66
     to
    0.65
    0.57
    st
    0.57
    ang
    0.55
     Road
    0.55
    ab
    0.53
     Declaration
    0.53
     Claim
    0.53
    Activations Density 0.000%

    No Known Activations