© 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. 35649
    Prev
    Next
    INDEX
    Explanations

    natural ways and history

    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
    t
    1.10
    o
    0.80
    r
    0.79
    en
    0.75
    n
    0.74
    l
    0.72
    ent
    0.68
    y
    0.57
     shocking
    0.53
    是
    0.53
    POSITIVE LOGITS
    д
    0.77
    یر
    0.74
     앞
    0.73
     has
    0.70
    твра
    0.69
    UM
    0.68
    ೖ
    0.68
     avoir
    0.66
    ㍍
    0.66
    ICK
    0.65
    Activations Density 0.003%

    No Known Activations