© 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. 81620
    Prev
    Next
    INDEX
    Explanations

    odontics, odontocetes, odontosaurs

    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
    是
    1.79
    M
    1.74
    P
    1.41
    L
    1.38
    كل
    1.37
    ↵↵
    1.36
    D
    1.36
    <0x0D>
    1.35
     of
    1.31
    A
    1.31
    POSITIVE LOGITS
    ри
    1.93
    ก
    1.69
    ם
    1.59
    ת
    1.55
    (
    1.53
    ی
    1.50
    ুল
    1.43
    که
    1.41
    رسی
    1.41
    ן
    1.36
    Activations Density 0.001%

    No Known Activations