© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174989
    Prev
    Next
    INDEX
    Explanations

    thinking about

    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_20_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
    chromosome
    0.47
    מונה
    0.45
    芷
    0.45
    Geocoder
    0.44
    لان
    0.44
     Pinnacle
    0.44
    ℤ
    0.44
    कील
    0.43
    下标
    0.43
    álás
    0.43
    POSITIVE LOGITS
     portray
    0.43
     markedly
    0.41
     fabrics
    0.41
    Curt
    0.40
     явно
    0.40
    яд
    0.39
     highly
    0.39
     அதற்கு
    0.39
    豊
    0.39
     constructs
    0.38
    Activations Density 0.003%

    No Known Activations