© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 137196
    Prev
    Next
    INDEX
    Explanations

    opt followed by 'us', 'iplex', 'us', 'mize', 'ician', 'ane', 'una', 'in'

    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_37_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
    нед
    0.50
    ('/:
    0.43
    мыс
    0.41
     bero
    0.39
     Burd
    0.39
     பண்ட
    0.38
    Republic
    0.38
    బ్బ
    0.38
    বেলা
    0.37
     perspect
    0.36
    POSITIVE LOGITS
     Truman
    0.39
    ภูมิ
    0.37
    hidupan
    0.37
    jeli
    0.37
    ọa
    0.37
     منی
    0.36
    試
    0.36
    ]]
    0.35
     للت
    0.35
    jén
    0.35
    Activations Density 0.001%

    No Known Activations