© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201252
    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_46_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
    isShow
    0.41
    urri
    0.40
    㷌
    0.40
    ucking
    0.40
    鿓
    0.38
    邨
    0.38
    εί
    0.37
     Snack
    0.37
     Singapura
    0.37
    ন্ব
    0.37
    POSITIVE LOGITS
     cosmos
    0.50
     للان
    0.40
     testen
    0.39
     Cosmos
    0.38
     космо
    0.37
    ቶችን
    0.37
     °,
    0.37
     test
    0.36
     prefix
    0.36
     contaminate
    0.36
    Activations Density 0.000%

    No Known Activations