© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88030
    Prev
    Next
    INDEX
    Explanations

    exponential growth

    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
    सँग
    0.86
    ד
    0.82
    ა
    0.73
    ק
    0.72
    dır
    0.68
    ر
    0.68
    ూ
    0.64
    یز
    0.62
    ي
    0.62
    ุ
    0.61
    POSITIVE LOGITS
    疃
    0.65
     défendre
    0.63
     souten
    0.63
     pessoal
    0.63
     besta
    0.62
     guérir
    0.62
     be
    0.61
     améli
    0.61
     respuesta
    0.60
    zi
    0.59
    Activations Density 0.001%

    No Known Activations