© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 87590
    Prev
    Next
    INDEX
    Explanations

    cloud services management

    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_3_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
    0.59
     bygg
    0.54
    ر
    0.54
    约翰
    0.53
    دهم
    0.52
    <0xBC>
    0.52
     weren
    0.51
    <0x8D>
    0.50
    <0x9F>
    0.50
    ARON
    0.50
    POSITIVE LOGITS
    of
    0.89
    <0x0D>
    0.86
     של
    0.71
     }}=\
    0.70
     électriques
    0.64
     کی
    0.63
     کل
    0.63
     مرکز
    0.62
    lovers
    0.61
     publicités
    0.61
    Activations Density 0.001%

    No Known Activations