© 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. 44766
    Prev
    Next
    INDEX
    Explanations

    prompt engineering and learning

    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
    w
    0.86
    h
    0.77
    ar
    0.75
    il
    0.75
    n
    0.73
    b
    0.71
    Edit
    0.71
    Sh
    0.70
    at
    0.68
    er
    0.67
    POSITIVE LOGITS
     is
    0.84
     کے
    0.73
    д
    0.70
     відео
    0.68
    ле
    0.66
     tights
    0.66
    ‌ترین
    0.65
     aliphatic
    0.64
    ำ
    0.64
    دود
    0.63
    Activations Density 0.004%

    No Known Activations