© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46820
    Prev
    Next
    INDEX
    Explanations

    post-independence developments

    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
    н
    0.83
    т
    0.70
    ン
    0.66
    که
    0.64
    роб
    0.64
    ками
    0.63
    テゴ
    0.62
    otted
    0.59
    with
    0.58
    ،
    0.56
    POSITIVE LOGITS
    OL
    0.74
    ad
    0.70
     at
    0.66
     is
    0.63
    ارو
    0.62
    ↵↵
    0.61
    ار
    0.59
     down
    0.58
    ارى
    0.57
    IN
    0.56
    Activations Density 0.002%

    No Known Activations