© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3950
    Prev
    Next
    INDEX
    Explanations

    name: task description

    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_39_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
    ಮಾಣ
    0.38
    neutral
    0.37
    anmar
    0.37
    ﾀ
    0.36
    遊戲
    0.36
    देवी
    0.36
    ဖ
    0.36
    bitmap
    0.36
     Manila
    0.36
    })$;
    0.36
    POSITIVE LOGITS
     enable
    0.44
    enable
    0.42
     Enable
    0.38
     Cosmo
    0.38
     upgrade
    0.37
     transfer
    0.36
     Azure
    0.36
     strukt
    0.36
     maintain
    0.36
     кос
    0.35
    Activations Density 0.011%

    No Known Activations