© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222530
    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
     collars
    0.57
     avocados
    0.51
    jell
    0.50
     झील
    0.50
    /
    0.50
     výro
    0.49
    殃
    0.49
     vhod
    0.48
     occurrences
    0.48
    兹
    0.48
    POSITIVE LOGITS
    ስ
    0.60
     ಅಥವಾ
    0.58
    ໃນ
    0.56
    ి
    0.55
    гу
    0.55
     га
    0.55
     Германия
    0.55
    レ
    0.55
    am
    0.54
    ementara
    0.54
    Activations Density 0.000%

    No Known Activations