© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78217
    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_53_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
     pearl
    0.47
     Pearl
    0.45
     pear
    0.42
     organised
    0.41
     L
    0.40
     organized
    0.40
     dok
    0.40
     pearls
    0.39
     Ivory
    0.39
    Pearl
    0.39
    POSITIVE LOGITS
     оку
    0.41
    tween
    0.39
    trecht
    0.38
    ்ய
    0.38
    ೃದ್ಧ
    0.38
     раство
    0.37
     profundamente
    0.37
    融
    0.37
    epte
    0.36
     profundidad
    0.36
    Activations Density 0.000%

    No Known Activations