© 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. 139564
    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
    ワイン
    0.43
    ordinating
    0.40
    Athena
    0.39
    혀
    0.39
     Eventually
    0.38
    omegranate
    0.38
    iguiente
    0.38
    ालत
    0.37
     ristorante
    0.37
    压
    0.37
    POSITIVE LOGITS
     можна
    0.43
     можно
    0.41
     ск
    0.41
     सुकून
    0.39
    Можно
    0.38
     można
    0.38
     weekend
    0.37
     lze
    0.36
     hom
    0.36
    кой
    0.35
    Activations Density 0.000%

    No Known Activations