© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24843
    Prev
    Next
    INDEX
    Explanations

    examples

    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_10_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
     be
    0.46
     comerci
    0.42
     наз
    0.40
     trece
    0.39
     inteligente
    0.38
     ג
    0.38
     desconocido
    0.38
     selecciona
    0.38
     দ্রব
    0.37
     tubes
    0.37
    POSITIVE LOGITS
     examples
    0.47
     Examples
    0.47
    examples
    0.45
    r
    0.45
    приклад
    0.45
     example
    0.44
    Examples
    0.44
    示例
    0.43
    example
    0.42
    EXAMPLE
    0.42
    Activations Density 0.138%

    No Known Activations