© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131070
    Prev
    Next
    INDEX
    Explanations

    alle

    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_6_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
    0.62
    ay
    0.59
    uk
    0.58
    ak
    0.54
    ԁ
    0.53
    arg
    0.51
    ও
    0.51
     breathtaking
    0.50
    ash
    0.50
    ang
    0.50
    POSITIVE LOGITS
    ۹
    0.72
    يط
    0.57
    وي
    0.56
    ון
    0.56
    of
    0.55
    מ
    0.55
    toDouble
    0.55
    in
    0.54
    رير
    0.53
    ље
    0.52
    Activations Density 0.000%

    No Known Activations