© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 33997
    Prev
    Next
    INDEX
    Explanations

    simplify the function

    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
    ilizar
    0.43
    ются
    0.37
     осталось
    0.37
    筺
    0.37
     изпол
    0.35
     ადამიან
    0.35
     парламента
    0.35
    ey
    0.34
    यान
    0.34
    गाव
    0.34
    POSITIVE LOGITS
     awe
    0.49
     pure
    0.46
    繫
    0.45
     before
    0.43
     snow
    0.42
     dodge
    0.41
     payroll
    0.41
     Wrath
    0.40
     धाम
    0.39
     Snap
    0.39
    Activations Density 0.006%

    No Known Activations