© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140759
    Prev
    Next
    INDEX
    Explanations

    gut, liver, and bowel anatomy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     messa
    0.54
     kunt
    0.53
    ressen
    0.52
    him
    0.52
     yard
    0.51
    ၇
    0.51
    肠
    0.50
     byt
    0.50
    тып
    0.49
    rody
    0.47
    POSITIVE LOGITS
    \
    0.64
     \
    0.55
    лее
    0.50
     die
    0.49
    सीएफ
    0.48
    ೆಗೆ
    0.48
     !\
    0.48
     கோ
    0.47
     considérons
    0.47
     embroidered
    0.46
    Activations Density 0.001%

    No Known Activations