© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33739
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
     দিনাজপুর
    0.36
    ൪
    0.35
    pea
    0.34
     TeV
    0.34
     molécules
    0.33
    reliance
    0.33
    arsis
    0.32
     मुलाकात
    0.32
     Ом
    0.32
    娄
    0.32
    POSITIVE LOGITS
    кий
    0.41
    findall
    0.37
     Biomed
    0.37
    }\|
    0.37
    eper
    0.36
    }^\
    0.36
     react
    0.35
     регистра
    0.35
     implement
    0.35
     hấp
    0.35
    Activations Density 0.000%

    No Known Activations