© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124790
    Prev
    Next
    INDEX
    Explanations

    salt baths and flats

    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
    ان
    0.72
    ו
    0.72
    ا
    0.69
    них
    0.66
    ні
    0.66
    (
    0.63
    th
    0.63
    ру
    0.63
    an
    0.62
    지
    0.61
    POSITIVE LOGITS
     in
    0.77
     I
    0.69
     Lithium
    0.68
     Հ
    0.62
     し
    0.60
     K
    0.60
     In
    0.59
     Neutron
    0.58
     stru
    0.57
     relates
    0.57
    Activations Density 0.000%

    No Known Activations