© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104992
    Prev
    Next
    INDEX
    Explanations

    German text with non-Latin characters

    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
    ed
    1.05
    et
    1.03
    i
    1.00
    ри
    0.97
    ت
    0.94
    il
    0.93
    ut
    0.88
    W
    0.86
    ag
    0.85
    oram
    0.85
    POSITIVE LOGITS
    ی
    1.49
    s
    1.11
    ă
    1.09
    ের
    1.09
    ς
    1.04
    𝑠
    1.02
    г
    0.92
    у
    0.91
    ب
    0.91
    ים
    0.90
    Activations Density 0.000%

    No Known Activations