© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17506
    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_34_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
    ॉम
    0.39
     Роди
    0.39
     Kaleidoscope
    0.38
     _,
    0.38
     Tokio
    0.38
     Glasgow
    0.37
     scallop
    0.37
     жени
    0.36
    _,
    0.36
     Ush
    0.36
    POSITIVE LOGITS
    ölf
    0.43
     پایه
    0.38
     యే
    0.38
     กว่า
    0.37
     phổi
    0.37
    ဇ
    0.36
    kový
    0.36
     tör
    0.34
    förm
    0.34
    getMonth
    0.33
    Activations Density 0.000%

    No Known Activations