© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216219
    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_16_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
     Made
    0.56
     Engine
    0.55
     적
    0.54
     Solution
    0.53
     Offered
    0.52
     Classic
    0.52
     Elevator
    0.51
    适
    0.51
     Suitable
    0.50
     Getter
    0.50
    POSITIVE LOGITS
    的女
    0.48
    Η
    0.48
     rū
    0.46
    ႃႇ
    0.46
     অনুষ্ঠ
    0.45
     juist
    0.43
     behest
    0.43
     осуществления
    0.42
     kuchh
    0.42
     interloc
    0.42
    Activations Density 0.000%

    No Known Activations