© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    4. 196334
    Prev
    Next
    INDEX
    Explanations

    specific items

    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_9_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
     ብዙውን
    0.47
    蜥
    0.45
     dictates
    0.44
     ወይም
    0.44
     ተጨማሪ
    0.44
     ጥቅም
    0.43
    ="#
    0.43
     নির্ণ
    0.41
     பெறு
    0.41
     generically
    0.41
    POSITIVE LOGITS
     Molecular
    0.54
    पी
    0.50
    ok
    0.49
     atención
    0.49
    مل
    0.47
    海
    0.47
     рис
    0.47
    ideen
    0.47
    ви
    0.46
    nen
    0.46
    Activations Density 0.000%

    No Known Activations