© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34537
    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_7_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
    ඨ
    0.54
    Pyrimidine
    0.53
    netHex
    0.52
    Tổng
    0.52
    стом
    0.51
    MathMarks
    0.51
    ଟ
    0.51
    STTS
    0.49
     спла
    0.49
    cích
    0.48
    POSITIVE LOGITS
    f
    0.66
     los
    0.56
     l
    0.54
     blanc
    0.53
     dip
    0.52
     limitada
    0.52
     Libertadores
    0.51
     singleton
    0.51
     libera
    0.51
     nadal
    0.50
    Activations Density 0.000%

    No Known Activations