© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116306
    Prev
    Next
    INDEX
    Explanations

    **detection of numerical units and scales**

    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_27_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
    gtk
    0.29
    特
    0.27
     guna
    0.27
    幽
    0.27
     হয়নি
    0.25
    全
    0.25
     humorous
    0.25
    datas
    0.25
     tam
    0.25
    アフ
    0.25
    POSITIVE LOGITS
     duquel
    0.33
     který
    0.33
     который
    0.31
     ktorý
    0.31
    getResponseCode
    0.30
     器
    0.30
    ष्टाचार
    0.30
     সহরের
    0.29
    賖
    0.29
     który
    0.28
    Activations Density 0.000%

    No Known Activations