© 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. 9301
    Prev
    Next
    INDEX
    Explanations

    breath hitched

    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
    டப்பட்டது
    0.40
    遭受
    0.38
    हारा
    0.36
     Blink
    0.36
    께서
    0.33
     Chile
    0.33
     FLASH
    0.33
    퉁
    0.33
     крас
    0.32
     отправ
    0.32
    POSITIVE LOGITS
    र्या
    0.38
    izh
    0.33
    形的
    0.32
    chard
    0.32
     hold
    0.32
     solver
    0.32
    gha
    0.31
    chini
    0.31
    amia
    0.31
     utiliz
    0.31
    Activations Density 0.003%

    No Known Activations