© 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. 80587
    Prev
    Next
    INDEX
    Explanations

    Lady Gaga

    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
     Kommun
    0.37
    osoma
    0.37
    깔
    0.36
     سہ
    0.35
     પડે
    0.35
    గో
    0.34
    丏
    0.34
    通讯
    0.34
    ள்க
    0.33
    চার্জ
    0.33
    POSITIVE LOGITS
    rugged
    0.40
     hinn
    0.37
     vant
    0.36
    avgs
    0.35
    获
    0.34
    zys
    0.33
    ទុក
    0.33
     harden
    0.33
     autant
    0.33
     snub
    0.32
    Activations Density 0.000%

    No Known Activations