© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16806
    Prev
    Next
    INDEX
    Explanations

    why it happens

    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_40_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
    君
    0.37
    네
    0.36
    oof
    0.35
     Gentlemen
    0.34
    retch
    0.33
    Pacific
    0.33
     процеду
    0.33
    ظ
    0.32
    யமாக
    0.32
     automating
    0.32
    POSITIVE LOGITS
     happen
    1.90
     happens
    1.84
     happened
    1.83
     happening
    1.80
     Happens
    1.70
     Happened
    1.58
     Happen
    1.56
    Happ
    1.54
    happ
    1.50
     aconteceu
    1.41
    Activations Density 0.234%

    No Known Activations