© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134114
    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_6_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
    ب
    1.10
    ian
    1.02
    *_
    0.94
    inin
    0.93
    amps
    0.91
    ars
    0.90
     was
    0.89
    adas
    0.88
    لم
    0.87
    فت
    0.86
    POSITIVE LOGITS
     cocina
    0.97
    ли
    0.96
     factura
    0.95
     with
    0.95
     conform
    0.95
     comprens
    0.95
    ை
    0.93
     máxima
    0.92
     usu
    0.91
     comedy
    0.90
    Activations Density 0.000%

    No Known Activations