© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138675
    Prev
    Next
    INDEX
    Explanations

    multiplication

    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_46_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
    umann
    0.38
     እነ
    0.38
    號
    0.38
    Clik
    0.36
    ходите
    0.36
    azion
    0.35
    겔
    0.35
    adda
    0.35
    馈
    0.35
    ailed
    0.34
    POSITIVE LOGITS
     x
    0.60
    ×
    0.45
     ×
    0.40
     nm
    0.39
    friendly
    0.39
     friendly
    0.38
     Priority
    0.38
     १७
    0.38
    ｘ
    0.37
     Webs
    0.37
    Activations Density 0.000%

    No Known Activations