© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38644
    Prev
    Next
    INDEX
    Explanations

    names and entities followed by descriptions or dates

    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_11_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
    waffe
    0.49
     Ports
    0.47
    posti
    0.46
     Spence
    0.46
     특히
    0.45
    ân
    0.45
    ঘাট
    0.45
    '},
    0.45
     अभिव्यक्ति
    0.45
     दिख
    0.44
    POSITIVE LOGITS
     ziem
    0.49
    bellar
    0.49
    стру
    0.49
     சுரே
    0.49
    ۟
    0.48
     ঝুল
    0.48
    蕖
    0.47
    ેલી
    0.47
    ⠀⠀⠀⠀
    0.46
     seafood
    0.45
    Activations Density 0.014%

    No Known Activations