© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99076
    Prev
    Next
    INDEX
    Explanations

    distinguishing contexts

    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_14_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
    C
    0.54
    Column
    0.51
          
    0.50
    增
    0.50
    estr
    0.48
    0
    0.48
    生育
    0.47
    厉害
    0.46
    column
    0.46
    高性能
    0.45
    POSITIVE LOGITS
     Cauchy
    0.55
     cigars
    0.55
    зумі
    0.54
     crash
    0.54
     shock
    0.53
     worrying
    0.52
     welfare
    0.51
    িয়াছি
    0.51
     tributaries
    0.50
     tilapia
    0.50
    Activations Density 0.000%

    No Known Activations