© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115505
    Prev
    Next
    INDEX
    Explanations

    table column definition

    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
     питания
    0.49
    𝗎
    0.41
     पैसा
    0.40
    🔆
    0.39
     📫
    0.39
    ਭ
    0.39
    🌰
    0.38
    ിൽ
    0.38
     potencial
    0.37
    俑
    0.36
    POSITIVE LOGITS
     Region
    0.41
     Boch
    0.38
     designated
    0.38
     Limit
    0.37
     limit
    0.36
     designate
    0.36
     vok
    0.36
    addock
    0.35
     Maud
    0.35
     Goddard
    0.35
    Activations Density 0.003%

    No Known Activations