© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233688
    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_46_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
    featured
    0.39
     제공
    0.39
    齐
    0.37
     fun
    0.37
     must
    0.36
    োক
    0.36
     Kw
    0.35
    备
    0.35
     empirical
    0.35
     Empirical
    0.35
    POSITIVE LOGITS
     Handic
    0.43
     CLOSE
    0.41
     lähe
    0.41
     nærm
    0.40
     läh
    0.39
     близ
    0.39
    的手
    0.38
     Tea
    0.38
    DISABLED
    0.38
     Certainly
    0.38
    Activations Density 0.000%

    No Known Activations