© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45805
    Prev
    Next
    INDEX
    Explanations

    life sciences

    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_3_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
    ه
    0.94
    يتي
    0.76
    ليس
    0.75
    اني
    0.72
    ల
    0.71
    نا
    0.68
    箓
    0.66
    料
    0.66
     يا
    0.65
     rempl
    0.64
    POSITIVE LOGITS
    )
    0.94
     in
    0.90
    ),
    0.78
    )`
    0.77
    )’
    0.74
    w
    0.74
    li
    0.70
    )")
    0.70
    )",
    0.70
    ;
    0.70
    Activations Density 0.010%

    No Known Activations