© 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. 233793
    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
     pollute
    0.36
    Limit
    0.36
     Limit
    0.36
     dekor
    0.36
     lernen
    0.35
     polarised
    0.35
    ภาษ
    0.35
    ບ
    0.35
    логі
    0.35
     شهید
    0.34
    POSITIVE LOGITS
    Earl
    0.39
     nerv
    0.37
     Scientists
    0.37
     Donald
    0.37
     BP
    0.37
    hyst
    0.36
     нер
    0.36
     instances
    0.36
     Marcel
    0.35
    彪
    0.35
    Activations Density 0.000%

    No Known Activations