© 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. 215267
    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
     releases
    0.38
    releases
    0.37
    蒙
    0.37
     TDS
    0.36
    Produ
    0.36
     bond
    0.35
    Uploaded
    0.35
    倍
    0.35
     tele
    0.35
     debt
    0.35
    POSITIVE LOGITS
    GoAbroad
    0.38
     seq
    0.37
     mermaid
    0.37
     crispy
    0.37
    経路
    0.36
    🙊
    0.36
    녕하세요
    0.36
    !<
    0.36
     मादा
    0.36
    ளான
    0.35
    Activations Density 0.000%

    No Known Activations