© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27753
    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_40_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
     `'\\
    0.50
    呤
    0.49
     বলিয়
    0.45
     دستاویز
    0.45
    らう
    0.44
    PathDirectory
    0.44
     vérifier
    0.44
    ᐳ
    0.44
    בות
    0.43
     quelquefois
    0.43
    POSITIVE LOGITS
     crush
    0.39
     inf
    0.39
     tal
    0.38
     Duke
    0.38
    hex
    0.38
     EV
    0.38
     Abre
    0.38
    ukov
    0.38
     Ex
    0.37
     z
    0.37
    Activations Density 0.000%

    No Known Activations