© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217737
    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_16_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
    <0x80>
    0.58
    و
    0.50
    _
    0.48
    O
    0.47
    \
    0.46
    |
    0.45
    ्रेड
    0.45
     apprentice
    0.45
    πο
    0.44
    ור
    0.44
    POSITIVE LOGITS
     рід
    0.54
     पॉप
    0.50
     fluttering
    0.49
     pesc
    0.49
     moms
    0.48
     शिला
    0.47
    <unused1011>
    0.47
    yii
    0.46
     whispering
    0.46
    মঙ্গল
    0.46
    Activations Density 0.000%

    No Known Activations