© 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. 144569
    Prev
    Next
    INDEX
    Explanations

    thinkers

    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
    i
    1.63
    b
    1.59
    ção
    1.50
    and
    1.44
     and
    1.24
    ized
    1.22
     mikä
    1.21
    ਮ
    1.18
    ade
    1.15
    me
    1.15
    POSITIVE LOGITS
    ли
    1.90
    ی
    1.90
    ।
    1.84
    s
    1.83
    ا۔
    1.64
    ים
    1.58
    ロ
    1.54
    ا
    1.52
    ের
    1.48
    س
    1.46
    Activations Density 0.000%

    No Known Activations