© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134495
    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
    t
    1.35
    ।
    1.16
    ။
    1.13
    ку
    1.09
    tahun
    1.06
    ၊
    1.05
     Ще
    1.00
    ur
    0.99
    transition
    0.97
    va
    0.96
    POSITIVE LOGITS
    1.10
    ה
    1.02
     sheath
    0.75
     seguir
    0.72
     parlor
    0.70
     fit
    0.70
     maneuver
    0.70
    с
    0.69
     oscillator
    0.68
    อี
    0.68
    Activations Density 0.000%

    No Known Activations