© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260431
    Prev
    Next
    INDEX
    Explanations

    subset, inputs, parameters

    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_22_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
    โก
    0.37
    贝
    0.35
     réaction
    0.33
     ఆలో
    0.33
    يار
    0.33
    行动
    0.33
    咁
    0.33
     কর্মকাণ্ড
    0.33
     që
    0.33
     comportement
    0.32
    POSITIVE LOGITS
    ami
    0.38
    ura
    0.37
    ọt
    0.34
    மில்லை
    0.34
    गुज
    0.33
    ahi
    0.33
    ⺊
    0.33
    endid
    0.33
     securely
    0.33
    Antae
    0.33
    Activations Density 0.000%

    No Known Activations