© 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. 198241
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    serrat
    0.40
    mehr
    0.40
    
    0.39
    樑
    0.38
    社員
    0.37
    泂
    0.37
    ERA
    0.36
    걀
    0.36
     دیکھا
    0.36
    ERNAL
    0.36
    POSITIVE LOGITS
     gourmet
    0.40
     opinion
    0.40
     Python
    0.40
     groundbreaking
    0.40
     paradise
    0.39
     non
    0.39
     textured
    0.39
     time
    0.38
     outcome
    0.37
     Directorate
    0.37
    Activations Density 0.011%

    No Known Activations