© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112979
    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_2_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
    )：
    1.17
    و
    1.16
     are
    1.15
    an
    1.10
    다
    1.03
    ：
    0.96
    )，
    0.95
    )
    0.93
    )',
    0.88
    ell
    0.87
    POSITIVE LOGITS
     by
    1.41
    ﺍ
    1.14
     (
    1.05
    Ⲧ
    1.02
    0.95
    મ
    0.93
     від
    0.91
    ଈ
    0.91
     bằng
    0.88
    篌
    0.86
    Activations Density 0.000%

    No Known Activations