© 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. 4205
    Prev
    Next
    INDEX
    Explanations

    Equal Opportunity Employer

    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
    client
    0.42
    "]="
    0.38
    Client
    0.38
    All
    0.37
    def
    0.37
    MouseEnter
    0.36
    urri
    0.36
    နည်း
    0.36
    五
    0.35
    Activate
    0.34
    POSITIVE LOGITS
    कारा
    0.43
     spécialistes
    0.40
     посла
    0.40
     loops
    0.39
     आधा
    0.38
     intern
    0.38
     allowance
    0.38
    幅度
    0.37
     Accountant
    0.37
    ienda
    0.37
    Activations Density 0.004%

    No Known Activations