© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32376
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and definitions

    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_31_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
     juxtaposition
    0.43
    フェア
    0.42
     burlap
    0.39
    ♰
    0.38
     conjunction
    0.38
     Fertil
    0.37
     ус
    0.37
     Filtration
    0.36
     fertiliser
    0.36
     Kamath
    0.36
    POSITIVE LOGITS
    住了
    0.44
    ://
    0.37
    属于
    0.36
     Toshiba
    0.35
    oda
    0.35
    邾
    0.35
    ierzchn
    0.35
    朐
    0.35
     Tok
    0.34
     पुनः
    0.34
    Activations Density 0.070%

    No Known Activations