© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144424
    Prev
    Next
    INDEX
    Explanations

    alignment and opacity values

    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_0_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
    ا
    2.31
     an
    1.84
    ו
    1.84
    ם
    1.84
    도
    1.80
    م
    1.80
    ing
    1.66
    un
    1.63
    ے
    1.62
    在
    1.61
    POSITIVE LOGITS
    儩
    1.24
    తో
    1.22
    フォト
    1.07
    bumptech
    1.07
    지는
    1.06
    什么
    1.05
    r
    1.05
    अनुसूचित
    1.03
    ప్రత్య
    1.02
    ཇ
    1.02
    Activations Density 0.000%

    No Known Activations