© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40306
    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_57_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
    Residence
    0.47
     residence
    0.42
     Residence
    0.40
     Cav
    0.39
    ুৎ
    0.39
     ’
    0.38
     Producing
    0.38
     Séb
    0.38
    δά
    0.37
     basically
    0.37
    POSITIVE LOGITS
    兌
    0.38
    湍
    0.37
    ترك
    0.36
    龕
    0.36
     пли
    0.35
    alade
    0.34
    ้าย
    0.34
     PLATE
    0.34
    ineux
    0.33
     yǐ
    0.33
    Activations Density 0.000%

    No Known Activations