© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161823
    Prev
    Next
    INDEX
    Explanations

    class of

    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_31_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
     Kombination
    0.42
    赘
    0.40
    scatterplot
    0.37
    雾
    0.37
     विश
    0.36
    ಂತೆ
    0.36
     combinação
    0.36
    狱
    0.36
     Kün
    0.36
    yle
    0.36
    POSITIVE LOGITS
     spoiled
    0.40
    饲
    0.37
    Видео
    0.37
    Processed
    0.36
    Pay
    0.36
     زمان
    0.35
     modernas
    0.35
     മത
    0.34
     weighed
    0.34
    Academy
    0.34
    Activations Density 0.006%

    No Known Activations