© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126406
    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_3_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
    ت
    0.82
    ول
    0.76
    d
    0.71
    ش
    0.70
    و
    0.70
    기
    0.66
    وف
    0.63
    স
    0.63
    }},
    0.61
    ש
    0.60
    POSITIVE LOGITS
    \
    0.99
     एकत्र
    0.66
     be
    0.66
     एकत्रित
    0.65
    ’
    0.65
     a
    0.63
     empezar
    0.62
     rit
    0.61
     incomparable
    0.61
     développe
    0.61
    Activations Density 0.000%

    No Known Activations