© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224305
    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_10_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
     asociaciones
    0.77
    ла
    0.76
    Adresse
    0.66
     Feuilles
    0.65
     Adresse
    0.65
    ंना
    0.64
     Осно
    0.63
    ố
    0.62
    них
    0.62
     Zustand
    0.62
    POSITIVE LOGITS
     be
    0.75
     to
    0.70
     breezy
    0.65
     whisky
    0.63
    ۲
    0.63
    <0xA5>
    0.61
     reef
    0.61
     உள்ளனர்
    0.59
     hunk
    0.59
    skinned
    0.59
    Activations Density 0.000%

    No Known Activations