© 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. 226868
    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
    an
    0.95
     .
    0.91
    ق
    0.90
    ير
    0.88
     porches
    0.87
    of
    0.85
    ма
    0.84
    न
    0.83
    9
    0.82
    4
    0.82
    POSITIVE LOGITS
    '
    1.38
    ري
    1.02
    ي
    1.00
    ু
    0.96
    า
    0.95
    с
    0.95
    ong
    0.93
    ('')
    0.91
    '}$
    0.91
    N
    0.90
    Activations Density 0.000%

    No Known Activations