© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52849
    Prev
    Next
    INDEX
    Explanations

    events and spaces

    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_30_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
    Header
    0.30
    ব্যবহার
    0.29
    唁
    0.29
    featured
    0.28
    相似
    0.28
    जि
    0.28
    ሩ
    0.28
    ữu
    0.27
    酒店
    0.27
    ছবি
    0.27
    POSITIVE LOGITS
     स्तन
    0.36
     Soccer
    0.35
     Guard
    0.33
     soccer
    0.32
     Swap
    0.32
     कॉन्फ्रेंस
    0.32
     swap
    0.32
     lunches
    0.32
     conference
    0.31
     footballer
    0.31
    Activations Density 0.002%

    No Known Activations