© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98482
    Prev
    Next
    INDEX
    Explanations

    fantasy races, guns, healthcare, products

    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_16_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
     говори
    0.52
     לע
    0.52
    ן
    0.49
     течение
    0.49
     recense
    0.47
     reorganize
    0.46
    тари
    0.46
     уважа
    0.45
     حبايبي
    0.45
    ণ্
    0.44
    POSITIVE LOGITS
    yd
    0.57
    esc
    0.53
    yp
    0.51
    â
    0.51
    uzi
    0.50
    esi
    0.48
    oge
    0.47
    esk
    0.46
    aging
    0.46
    å
    0.46
    Activations Density 0.000%

    No Known Activations