© 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. 171899
    Prev
    Next
    INDEX
    Explanations

    forward slash

    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
    פר
    0.46
    Economic
    0.43
     क
    0.42
    тий
    0.41
     Спо
    0.41
    គួរ
    0.41
     छुपा
    0.40
    Tai
    0.40
     Бекер
    0.39
     Tai
    0.39
    POSITIVE LOGITS
    驥
    0.42
    が一
    0.42
     først
    0.41
     ورځ
    0.40
    ນິກ
    0.39
     firing
    0.39
     musicale
    0.39
    বস
    0.39
     certes
    0.38
    য়াছে
    0.38
    Activations Density 0.004%

    No Known Activations