© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102712
    Prev
    Next
    INDEX
    Explanations

    properly working

    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_14_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
     Матери
    0.46
     Monte
    0.44
     Ко
    0.44
     совсем
    0.41
    Monte
    0.41
     endured
    0.40
     Э
    0.39
     Пла
    0.39
    شاه
    0.39
    mund
    0.38
    POSITIVE LOGITS
    ены
    0.56
    <unused7>
    0.50
    )。
    0.50
    剔
    0.47
     گے۔
    0.46
     divergents
    0.45
     Chill
    0.45
    
    0.45
     important
    0.44
    )>
    0.44
    Activations Density 0.000%

    No Known Activations