© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174650
    Prev
    Next
    INDEX
    Explanations

    celebrations, holidays, foundations, roles

    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
     velocities
    0.43
     energetics
    0.34
     kori
    0.33
     considérons
    0.33
    ्यूज
    0.33
    疝
    0.33
    櫸
    0.33
    юнча
    0.33
     spongy
    0.33
     acry
    0.32
    POSITIVE LOGITS
     an
    0.41
    could
    0.37
     could
    0.36
     pourrait
    0.36
    他们
    0.36
     apparently
    0.35
    敨
    0.35
    แมนเชสเตอร์
    0.34
     Manchester
    0.34
     può
    0.34
    Activations Density 0.032%

    No Known Activations