© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87352
    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_23_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
    これも
    0.48
     supposed
    0.47
    grown
    0.40
     >=
    0.40
     paraphernalia
    0.39
    you
    0.39
    ilus
    0.39
     apoptosis
    0.39
     dilap
    0.38
    appar
    0.38
    POSITIVE LOGITS
     kültür
    0.49
    విద్య
    0.47
     മെ
    0.45
     klima
    0.45
     ওয়েবসাইট
    0.45
     സ
    0.44
     griech
    0.44
     લગ
    0.44
    වුන්
    0.43
     दक्षिण
    0.42
    Activations Density 0.000%

    No Known Activations