© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228132
    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_6_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
    0.95
     այ
    0.89
     כול
    0.86
     կ
    0.85
     (\
    0.83
     mqtt
    0.80
     lete
    0.80
     čís
    0.79
     пред
    0.78
     rake
    0.77
    POSITIVE LOGITS
    )
    1.14
    b
    0.98
    n
    0.95
    are
    0.92
    from
    0.91
    jší
    0.91
    به
    0.91
    জ
    0.90
    "
    0.89
    𝙃
    0.89
    Activations Density 0.000%

    No Known Activations