© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167637
    Prev
    Next
    INDEX
    Explanations

    **numbers or math problems**

    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
    ไม่มี
    0.40
    开放
    0.38
     Lynd
    0.38
     کیل
    0.36
     Oswego
    0.36
    镀
    0.35
    entum
    0.35
    eit
    0.34
     Infections
    0.34
     Citibank
    0.34
    POSITIVE LOGITS
     wakati
    0.40
     atth
    0.38
     ಕನ
    0.37
     وتب
    0.36
     returnPacket
    0.35
     noqa
    0.35
     bxa
    0.34
    )):
    0.34
     سلاٹ
    0.34
     FRAME
    0.34
    Activations Density 0.000%

    No Known Activations