© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29800
    Prev
    Next
    INDEX
    Explanations

    match case statements

    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_40_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
    ivary
    0.38
     act
    0.36
    sees
    0.36
    しまい
    0.35
     joy
    0.35
    销售
    0.35
     акты
    0.35
     --
    0.35
    ysed
    0.35
    inese
    0.34
    POSITIVE LOGITS
     kịp
    0.42
     पथ
    0.40
    აც
    0.39
    Visitor
    0.39
     descripción
    0.38
    প্রিল
    0.37
    ாளர்க
    0.36
    ர்களில்
    0.36
     decid
    0.36
     সঞ্জীবনী
    0.36
    Activations Density 0.001%

    No Known Activations