© 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. 107391
    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
     a
    0.91
     for
    0.85
     be
    0.78
     z
    0.78
     d
    0.77
     can
    0.76
     b
    0.75
     l
    0.75
     h
    0.72
     p
    0.71
    POSITIVE LOGITS
    할
    0.79
    ки
    0.78
    that
    0.70
    있
    0.69
    들이
    0.68
    나
    0.68
    u
    0.67
    ಯ
    0.66
    정이
    0.64
    εις
    0.63
    Activations Density 0.000%

    No Known Activations