© 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. 144711
    Prev
    Next
    INDEX
    Explanations

    silicon dioxide

    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
    ᱑
    1.63
     حتی
    1.61
    ۰
    1.60
    できる
    1.59
     لی
    1.59
    த்தில்
    1.54
     cambi
    1.51
    ின்
    1.49
     deont
    1.48
     وہ
    1.46
    POSITIVE LOGITS
    -
    2.58
    و
    2.50
    /
    2.30
    '
    2.22
    i
    2.13
    "
    1.97
    at
    1.91
    *
    1.91
    an
    1.80
    ي
    1.72
    Activations Density 0.000%

    No Known Activations