© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117807
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

    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_27_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
    LabelTool
    0.39
    ىڭ
    0.37
    적
    0.35
     onChanged
    0.35
    卋
    0.33
     ಕನ್ನಡ
    0.33
    㭂
    0.33
    슷
    0.33
     पा
    0.32
     TypeToken
    0.32
    POSITIVE LOGITS
    udah
    0.33
    oyo
    0.32
     ሂደ
    0.31
     managerial
    0.31
     formalities
    0.31
     सारा
    0.30
    jou
    0.30
    accompagn
    0.30
    ere
    0.29
    volt
    0.29
    Activations Density 0.002%

    No Known Activations