© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66589
    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_51_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
    氓
    0.43
    makedirs
    0.38
    داث
    0.38
    leukin
    0.36
    🠀
    0.36
    datatype
    0.36
    tesla
    0.36
     TID
    0.36
     pulumi
    0.36
    Rename
    0.35
    POSITIVE LOGITS
    సో
    0.44
     Som
    0.42
    沱
    0.42
    Som
    0.40
     acert
    0.40
     nyeri
    0.38
     Ush
    0.37
     rectangles
    0.37
     scritt
    0.37
     fér
    0.37
    Activations Density 0.000%

    No Known Activations