© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110788
    Prev
    Next
    INDEX
    Explanations

    an omen

    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_2_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
    é
    1.32
    is
    1.25
    ق
    1.23
    ت
    1.22
    ल
    1.19
    1.16
    _
    1.07
    y
    1.05
    k
    1.05
    la
    1.03
    POSITIVE LOGITS
    ان
    0.92
    った
    0.84
    ado
    0.82
    ার
    0.82
    える
    0.79
    లు
    0.75
    斗
    0.75
    ти
    0.75
    か
    0.73
    し
    0.73
    Activations Density 0.000%

    No Known Activations