© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50606
    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_10_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
    o
    0.51
     Dighe
    0.50
     எடுத்து
    0.47
    тие
    0.46
     इंच
    0.46
    âteaux
    0.46
    пер
    0.45
    煜
    0.45
    <0x86>
    0.45
    ▭
    0.45
    POSITIVE LOGITS
    Че
    0.49
     an
    0.47
    Beginning
    0.45
    Starting
    0.45
     saturation
    0.45
    Chia
    0.44
    Breakpoint
    0.43
    나
    0.43
     healing
    0.43
     finishing
    0.43
    Activations Density 0.000%

    No Known Activations