© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210924
    Prev
    Next
    INDEX
    Explanations

    varieties

    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_5_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
     to
    0.95
     on
    0.94
    ↵↵
    0.91
     será
    0.89
    不少
    0.89
    ви
    0.88
    ↵
    0.86
    م
    0.83
    pesar
    0.83
    ы
    0.83
    POSITIVE LOGITS
    i
    1.82
    it
    1.79
    p
    1.52
    r
    1.38
    on
    1.38
    al
    1.38
    et
    1.35
    ar
    1.22
    ol
    1.22
    iin
    1.21
    Activations Density 0.000%

    No Known Activations