© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225356
    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_10_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
     książ
    0.54
     wouldn
    0.53
    स्टिव
    0.52
     I
    0.49
    ław
    0.48
    取り付け
    0.48
     Bumi
    0.48
     correr
    0.48
     shrew
    0.47
     seconded
    0.47
    POSITIVE LOGITS
    на
    0.59
    গ
    0.59
     upsetting
    0.57
    ম
    0.57
    rigues
    0.54
    RAS
    0.53
    দের
    0.52
    acts
    0.50
    ಗಳಿವೆ
    0.49
    ବା
    0.47
    Activations Density 0.000%

    No Known Activations