© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131735
    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_6_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
    Ε
    0.89
     égal
    0.84
    каз
    0.80
     hémorro
    0.80
     élus
    0.79
    Б
    0.79
     caoutch
    0.78
    US
    0.77
    شر
    0.77
    Че
    0.77
    POSITIVE LOGITS
    os
    1.60
    ate
    1.53
    are
    1.45
    um
    1.25
    ada
    1.24
    é
    1.23
    ans
    1.23
    et
    1.22
    ai
    1.22
    ik
    1.20
    Activations Density 0.000%

    No Known Activations