© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197919
    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_9_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
    д
    0.66
    м
    0.64
    𝕥
    0.59
    𝗱
    0.59
    ли
    0.56
    くらい
    0.56
    𝐛
    0.56
    Ừ
    0.55
     တယ်
    0.54
    տ
    0.54
    POSITIVE LOGITS
     I
    0.72
     Cip
    0.56
     Jep
    0.53
     Culver
    0.49
    ol
    0.49
     Trades
    0.49
     Cust
    0.48
     gars
    0.48
     Dolce
    0.48
     Don
    0.48
    Activations Density 0.000%

    No Known Activations