© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131699
    Prev
    Next
    INDEX
    Explanations

    Galápagos; Desert; Andes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    .
    1.25
    ا
    0.95
    !
    0.93
    tä
    0.93
    问题
    0.89
    "
    0.87
    Problem
    0.84
     Africa
    0.82
     Hills
    0.81
    است
    0.79
    POSITIVE LOGITS
    ור
    1.47
     μία
    1.24
    са
    1.21
    ха
    1.14
    ща
    1.13
    ни
    1.09
    ви
    1.08
     civiles
    1.08
    ૦
    1.05
    ы
    1.04
    Activations Density 0.000%

    No Known Activations