© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167780
    Prev
    Next
    INDEX
    Explanations

    calculate division or subtraction

    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_34_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
    друг
    0.36
    ('-');
    0.35
    用戶
    0.34
     CLUB
    0.33
    ZERO
    0.33
    밖에
    0.33
     уйнау
    0.32
    стана
    0.32
     يطلع
    0.31
    ``.
    0.31
    POSITIVE LOGITS
    व्यापी
    0.40
     Shoe
    0.36
     Sphere
    0.36
     drier
    0.36
    ுமா
    0.34
    edown
    0.33
    ሣ
    0.33
    rectionType
    0.33
    Sou
    0.33
     symptom
    0.32
    Activations Density 0.004%

    No Known Activations