© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199173
    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_27_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
     dadurch
    0.50
     yaparak
    0.45
    merry
    0.43
     majeur
    0.41
    PrintWriter
    0.41
     zbyt
    0.41
    starcore
    0.40
    ｨ
    0.40
    setzen
    0.40
    룽
    0.40
    POSITIVE LOGITS
     Smart
    0.50
     Chemical
    0.42
     Chem
    0.41
     Field
    0.41
     Mod
    0.39
     Fe
    0.39
     Solutions
    0.39
     Boe
    0.39
     Visual
    0.39
     Lab
    0.38
    Activations Density 0.000%

    No Known Activations