© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181101
    Prev
    Next
    INDEX
    Explanations

    Rapid Support Forces

    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_24_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
    ium
    0.39
    '),
    0.39
    ारी
    0.37
     '':
    0.37
    uvi
    0.37
    रिक्
    0.36
    ').
    0.35
     fps
    0.35
     xxx
    0.34
    ):
    0.34
    POSITIVE LOGITS
    ╧
    0.48
     বলেই
    0.41
     Ciencia
    0.41
     Flatten
    0.40
    itorios
    0.40
     Coulomb
    0.39
    ManagerPortal
    0.39
    
    0.39
     গুল
    0.38
     conditionals
    0.38
    Activations Density 0.001%

    No Known Activations