© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 164826
    Prev
    Next
    INDEX
    Explanations

    digit sums

    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_13_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
    an
    0.63
     אל
    0.58
     न्यूमेरिकल
    0.57
    値
    0.55
     podle
    0.55
     empirically
    0.54
    数値
    0.54
    '
    0.54
     DEI
    0.53
     numerical
    0.53
    POSITIVE LOGITS
    ff
    0.65
    sections
    0.64
    ಿಕ
    0.61
    cwd
    0.61
    ológicas
    0.61
    ning
    0.60
    ns
    0.60
    sp
    0.59
    up
    0.59
    topics
    0.59
    Activations Density 0.018%

    No Known Activations