© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93222
    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_11_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
     overlays
    0.49
    ⇨
    0.46
     affairs
    0.45
    קל
    0.45
    я
    0.45
     waffles
    0.44
     recorders
    0.44
    ಸ್
    0.43
     additions
    0.42
     barges
    0.42
    POSITIVE LOGITS
     lineare
    0.57
    <unused1047>
    0.54
     قصير
    0.52
    কারীর
    0.50
     நூற்றாண்டின்
    0.50
     bạc
    0.50
     لين
    0.49
     rougeâtres
    0.49
     statistique
    0.48
    getahuan
    0.47
    Activations Density 0.000%

    No Known Activations