© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252866
    Prev
    Next
    INDEX
    Explanations

    assignment operator

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Alas
    0.39
     invitados
    0.38
     î
    0.37
     যতক্ষণ
    0.35
     Paulo
    0.35
    ┊
    0.35
     啊
    0.34
    ․
    0.34
    ❻
    0.33
     alas
    0.33
    POSITIVE LOGITS
     =
    1.84
     $=$
    1.63
    =
    1.60
     $=\
    1.59
     $=
    1.54
    ＝
    1.54
    
    1.32
     =\
    1.31
    =\
    1.30
     +=
    1.29
    Activations Density 0.053%

    No Known Activations