© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193652
    Prev
    Next
    INDEX
    Explanations

    baryonic mass

    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_27_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
     registry
    0.33
     registro
    0.32
     Primer
    0.31
    䣬
    0.29
     normalize
    0.29
     boardroom
    0.29
     организова
    0.28
     Primeiro
    0.28
     analytic
    0.28
     tribu
    0.28
    POSITIVE LOGITS
    Acknowledgement
    0.30
    ♠
    0.29
    
    0.29
    ="#
    0.28
    mment
    0.28
    ził
    0.28
     методом
    0.28
    انه
    0.28
     emphasised
    0.28
     emphasises
    0.27
    Activations Density 0.000%

    No Known Activations