© 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. 200861
    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
    an
    1.31
    ER
    1.29
    the
    1.20
    ری
    1.11
    s
    1.06
    ان
    1.05
    UT
    1.04
    to
    1.02
    er
    0.99
     an
    0.97
    POSITIVE LOGITS
    د
    1.00
     dukkham
    0.80
    就像
    0.79
     superstructure
    0.77
    íž
    0.76
     restricciones
    0.76
     SLAs
    0.76
     notor
    0.75
     observaciones
    0.75
    ﺑ
    0.75
    Activations Density 0.000%

    No Known Activations