© 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. 43489
    Prev
    Next
    INDEX
    Explanations

    GMRS radios

    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
    ድግዳ
    0.71
    nosis
    0.70
     उमेदवार
    0.70
    nay
    0.68
    nou
    0.68
    ม
    0.68
    पूर्ति
    0.66
    nogo
    0.66
    nál
    0.64
     друго
    0.64
    POSITIVE LOGITS
    in
    1.03
    、
    0.77
    в
    0.70
    し
    0.70
    きの
    0.67
    h
    0.64
    c
    0.61
    ৭
    0.61
    ،
    0.60
    くなる
    0.59
    Activations Density 0.002%

    No Known Activations