© 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. 157708
    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
    터
    1.04
    ，
    0.96
    </h3>
    0.91
     única
    0.91
     espírito
    0.91
     poderosa
    0.90
     pesar
    0.89
     física
    0.88
     阅读全文
    0.88
    </h2>
    0.88
    POSITIVE LOGITS
    '
    1.91
    is
    1.67
    د
    1.55
    de
    1.50
    us
    1.46
    ana
    1.44
    d
    1.41
    _
    1.39
    in
    1.38
    t
    1.35
    Activations Density 0.000%

    No Known Activations