© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1641
    Prev
    Next
    INDEX
    Explanations

    disassemble Smali assembly

    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_39_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
    fters
    0.45
     DOF
    0.37
    Blocking
    0.36
     bpy
    0.35
    鏝
    0.35
    ेडियम
    0.34
     logarith
    0.34
     чемпионате
    0.34
    プロセス
    0.33
    left
    0.33
    POSITIVE LOGITS
     dismantle
    0.53
     disassemble
    0.53
    拆
    0.52
     dismantled
    0.51
     dismantling
    0.48
     dismant
    0.45
     disassembled
    0.44
     Dism
    0.41
     torn
    0.39
     lib
    0.38
    Activations Density 0.019%

    No Known Activations