© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17319
    Prev
    Next
    INDEX
    Explanations

    fragmentation and regeneration

    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_34_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
     ఖాత
    0.38
     ట్రా
    0.37
     краси
    0.36
     xhrObj
    0.36
     پیشنه
    0.36
    क्रीम
    0.36
    $-(
    0.36
    
    0.36
     বান্ধবী
    0.35
    :'],
    0.35
    POSITIVE LOGITS
     fragments
    0.71
     fragmentation
    0.71
     Fragment
    0.67
     fragmented
    0.67
    Fragment
    0.66
     fragment
    0.66
     regenerate
    0.65
    fragments
    0.64
    fragment
    0.63
    Fragmentation
    0.63
    Activations Density 0.019%

    No Known Activations