© 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. 30097
    Prev
    Next
    INDEX
    Explanations

    cpp code blocks

    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
    ❈
    0.42
    Democrats
    0.39
    စာ
    0.37
     aporta
    0.37
    CHD
    0.36
    课堂
    0.36
     qr
    0.36
    CSR
    0.36
    গার্ড
    0.36
    stocked
    0.35
    POSITIVE LOGITS
    屶
    0.47
     पिला
    0.42
    癜
    0.40
    惭
    0.38
     Brad
    0.37
    сиона
    0.37
     styles
    0.35
    দৌ
    0.35
    amb
    0.35
    孀
    0.35
    Activations Density 0.000%

    No Known Activations