© 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. 158949
    Prev
    Next
    INDEX
    Explanations

    Chinese Pinyin fragments

    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
    ys
    1.44
    0
    1.36
     for
    1.30
    ink
    1.19
    inn
    1.19
    ac
    1.18
    ire
    1.15
    ii
    1.15
    yd
    1.14
    ili
    1.13
    POSITIVE LOGITS
    s
    2.42
    ের
    1.78
    ség
    1.56
    ی
    1.52
    س
    1.49
    కు
    1.48
    માં
    1.44
    ्स
    1.43
    де
    1.42
    هاي
    1.40
    Activations Density 0.000%

    No Known Activations