© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32900
    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_40_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
    徕
    0.38
     पट
    0.38
     /
    0.38
     Charged
    0.38
     Acoustics
    0.38
    Hack
    0.37
     Hack
    0.37
     ·
    0.37
     Speck
    0.36
     Mileage
    0.36
    POSITIVE LOGITS
    upar
    0.40
    ണ്ണ
    0.38
    RICT
    0.37
    pring
    0.35
    onso
    0.35
    民國
    0.35
    沘
    0.35
     mandar
    0.35
    ঠাকুর
    0.35
    ÊN
    0.35
    Activations Density 0.000%

    No Known Activations