© 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. 144855
    Prev
    Next
    INDEX
    Explanations

    debt ceiling

    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
    تين
    1.66
    یہ
    1.63
    یه
    1.63
    る
    1.61
    ی
    1.56
    ת
    1.55
    ларга
    1.48
    :
    1.48
    고
    1.44
    ים
    1.42
    POSITIVE LOGITS
    p
    1.90
    f
    1.86
    .
    1.80
    to
    1.69
    the
    1.66
    ale
    1.59
    ne
    1.58
    an
    1.56
    r
    1.49
    z
    1.49
    Activations Density 0.001%

    No Known Activations