© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130704
    Prev
    Next
    INDEX
    Explanations

    ob followed by specific word parts

    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_1_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
    م
    1.28
    ie
    1.17
    er
    1.16
    in
    1.14
    el
    1.13
    i
    1.13
    en
    1.12
    d
    1.11
    at
    1.08
    ب
    1.08
    POSITIVE LOGITS
    س
    1.01
    с
    0.94
    ス
    0.91
    И
    0.90
    斯
    0.87
    》（
    0.83
    '}}
    0.82
    』（
    0.81
    shoes
    0.80
    `}
    0.79
    Activations Density 0.001%

    No Known Activations