© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30330
    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_7_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
    practice
    0.57
    campus
    0.50
    c
    0.48
    ال
    0.48
    自动
    0.47
    linkedin
    0.47
    ICE
    0.45
    个
    0.45
    am
    0.45
    mc
    0.45
    POSITIVE LOGITS
     ори
    0.60
     smother
    0.60
     bolstered
    0.59
     astonished
    0.58
     orientación
    0.56
     oficialmente
    0.56
     restable
    0.56
     suffoc
    0.55
     reinvigor
    0.55
     anodes
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.