© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76155
    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_31_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
    瑆
    0.40
     Filip
    0.37
     mime
    0.36
    ئه
    0.36
    THROW
    0.36
    πομπ
    0.35
    믹
    0.35
    hemeral
    0.35
    OGRAPHY
    0.34
    وتي
    0.34
    POSITIVE LOGITS
    phase
    0.40
    straight
    0.36
     Arlington
    0.36
    interest
    0.35
     interest
    0.33
     vectors
    0.33
    [[
    0.33
    bitflag
    0.33
     straight
    0.33
    strategic
    0.33
    Activations Density 0.000%

    No Known Activations