© 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. 49092
    Prev
    Next
    INDEX
    Explanations

    def or function followed by an action

    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
    娃
    0.38
     タイプ
    0.37
    㙋
    0.36
    石头
    0.36
    㠱
    0.35
    သည့်
    0.35
    鲫
    0.34
    但不
    0.33
     الرقم
    0.33
     깊
    0.33
    POSITIVE LOGITS
    eters
    0.40
    یسی
    0.36
    ped
    0.35
     tere
    0.35
     Buccaneers
    0.34
    reciate
    0.34
    eq
    0.33
    available
    0.33
    bs
    0.32
    icked
    0.32
    Activations Density 0.013%

    No Known Activations