© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164152
    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_31_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
     lost
    0.37
    靠
    0.37
    sections
    0.36
    芥
    0.35
    しま
    0.34
    回
    0.34
     中央
    0.34
    Lett
    0.34
    羍
    0.34
     Philosoph
    0.33
    POSITIVE LOGITS
     Predicting
    0.43
    hões
    0.42
     studios
    0.39
     monof
    0.39
     contralateral
    0.39
     matéri
    0.38
     fiyat
    0.38
     suelos
    0.38
     mentoring
    0.38
     colleges
    0.38
    Activations Density 0.000%

    No Known Activations