© 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. 145059
    Prev
    Next
    INDEX
    Explanations

    hearth and fireplace

    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
    ли
    1.65
    ب
    1.64
    ו
    1.58
     not
    1.34
    你
    1.28
    in
    1.23
    oğlu
    1.18
    لي
    1.16
    و
    1.16
    ন
    1.13
    POSITIVE LOGITS
    .
    1.90
    ่า
    1.56
     of
    1.44
    ри
    1.38
    یم
    1.33
    ні
    1.30
    리
    1.30
    いて
    1.26
    ер
    1.23
    arin
    1.23
    Activations Density 0.000%

    No Known Activations