© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134519
    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_37_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
     сіль
    0.37
     士
    0.37
     Closet
    0.37
    Municipal
    0.37
    た
    0.37
    💅
    0.37
     जैविक
    0.37
     Liquor
    0.36
    蝓
    0.36
    経過
    0.35
    POSITIVE LOGITS
     Honda
    0.80
    Honda
    0.79
     Volvo
    0.73
     خودرو
    0.71
     automaker
    0.69
     Fahrzeug
    0.68
     honda
    0.67
     powertrain
    0.67
     Chevrolet
    0.67
     bmw
    0.66
    Activations Density 0.000%

    No Known Activations