© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 5447
    Prev
    Next
    INDEX
    Explanations

    modal verbs and "it"

    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_40_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
     ქვე
    0.44
    是一
    0.39
     subtitles
    0.39
     Marcia
    0.38
     tapestry
    0.37
     ①
    0.37
     करवाना
    0.37
    ດ້ານ
    0.35
    ꧂
    0.35
     તરફ
    0.35
    POSITIVE LOGITS
    ’
    0.74
    ّ
    0.56
    <0x19>
    0.55
    ’
    0.53
    '
    0.51
    َّ
    0.46
    ّه
    0.44
    َّ
    0.42
    ´
    0.42
    \'
    0.41
    Activations Density 0.424%

    No Known Activations