© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31984
    Prev
    Next
    INDEX
    Explanations

    math calculations involving numbers

    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
     теперь
    0.48
     Теперь
    0.45
    얌
    0.44
    이제
    0.42
     now
    0.41
    Correlation
    0.40
     Jetzt
    0.38
    now
    0.38
    鬚
    0.37
    अब
    0.36
    POSITIVE LOGITS
     Senior
    0.41
     Unde
    0.41
     Ramsay
    0.39
     Unle
    0.38
     Visit
    0.38
    Senior
    0.37
     Spotlight
    0.36
    udere
    0.36
    elho
    0.36
    Running
    0.35
    Activations Density 0.002%

    No Known Activations