© 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. 52327
    Prev
    Next
    INDEX
    Explanations

    global variable creation or modification

    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
    条件的
    0.38
    ဩ
    0.38
    غو
    0.38
    条件
    0.38
    ฝ
    0.36
    tabname
    0.36
    條件
    0.35
     Loco
    0.35
    rach
    0.35
    门
    0.35
    POSITIVE LOGITS
     بأ
    0.46
    හැ
    0.41
    ULE
    0.37
     смер
    0.37
    lacian
    0.37
     Inside
    0.37
     досто
    0.37
     inside
    0.36
     दिला
    0.36
     достав
    0.36
    Activations Density 0.004%

    No Known Activations