© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88990
    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_11_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
     codons
    0.61
    ;
    0.58
    پ
    0.55
    అ
    0.55
     contributions
    0.54
     intentions
    0.54
     ('
    0.54
    Β
    0.52
     albums
    0.52
     lyrics
    0.52
    POSITIVE LOGITS
    ութ
    0.66
    複雑
    0.64
     disgruntled
    0.63
    ﺲ
    0.63
     těž
    0.61
     gloomy
    0.61
    álně
    0.59
    INFE
    0.59
     сложно
    0.59
    𝚕
    0.59
    Activations Density 0.000%

    No Known Activations