© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232649
    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_32_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
     privil
    0.38
    દેશ
    0.37
     خیال
    0.37
     empat
    0.36
     trộn
    0.36
    žić
    0.36
     регла
    0.36
    佷
    0.35
     mrs
    0.35
    റിയി
    0.35
    POSITIVE LOGITS
    UQ
    0.38
    columns
    0.37
    PU
    0.36
     اخذنا
    0.36
    auk
    0.35
     entw
    0.35
    输
    0.35
    Unit
    0.34
    өк
    0.34
    יוחד
    0.34
    Activations Density 0.000%

    No Known Activations