© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218586
    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_31_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
    ·
    0.41
    sma
    0.36
    '].
    0.35
    Wat
    0.35
     الصف
    0.35
     Sociales
    0.35
    '-
    0.34
    veland
    0.34
     %,
    0.34
     Gaston
    0.34
    POSITIVE LOGITS
    <unused66>
    0.42
     FAL
    0.40
     yanı
    0.38
    UTCTime
    0.38
    declaration
    0.38
     RCP
    0.38
     vegetable
    0.37
    reflectionCamera
    0.37
     krv
    0.37
    icoli
    0.37
    Activations Density 0.000%

    No Known Activations