© 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. 241571
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Sauber
    0.41
    要素
    0.38
    輝
    0.36
    コスト
    0.36
    )}{\
    0.36
     tropos
    0.36
     navigable
    0.35
    HK
    0.35
     Access
    0.35
     уро
    0.35
    POSITIVE LOGITS
    delay
    0.44
     delay
    0.42
    Delay
    0.39
     delaying
    0.39
    <unused63>
    0.39
    бит
    0.38
     delays
    0.37
    Dm
    0.37
    ället
    0.37
    maketitle
    0.36
    Activations Density 0.002%

    No Known Activations