© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176074
    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_20_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
     keyboard
    0.46
     weighs
    0.45
     pants
    0.43
    EY
    0.42
     allows
    0.42
     animation
    0.41
    ↵
    0.41
    CPU
    0.41
     phe
    0.41
    IRD
    0.41
    POSITIVE LOGITS
    稒
    0.58
    浧
    0.55
    الم
    0.54
     Sicherheits
    0.53
    ằng
    0.53
    苚
    0.52
    侢
    0.51
     Supervision
    0.50
    泹
    0.50
    浾
    0.50
    Activations Density 0.000%

    No Known Activations