© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 167
    Prev
    Next
    INDEX
    Explanations

    communities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     पकड़
    0.40
    ansom
    0.39
    ♀
    0.38
    養
    0.36
     पेड़
    0.36
    iume
    0.35
    uyang
    0.35
     عمرو
    0.35
    пень
    0.35
    ♂
    0.34
    POSITIVE LOGITS
     assembl
    0.91
     communities
    0.87
     assemblage
    0.86
    assembl
    0.86
     community
    0.85
     assemblages
    0.82
    Assembl
    0.81
     assembly
    0.80
    community
    0.79
     comunidad
    0.77
    Activations Density 0.021%

    No Known Activations