© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168398
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    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
    end
    0.47
    endu
    0.43
     seit
    0.42
     since
    0.41
    otur
    0.39
    otrich
    0.38
    mz
    0.38
    端
    0.38
    ijk
    0.38
    ีด
    0.38
    POSITIVE LOGITS
     αί
    0.41
    ამდ
    0.39
     evenings
    0.39
     inwon
    0.38
     Streets
    0.37
    Gab
    0.36
    身的
    0.36
    
    0.35
    
    0.35
    ======
    0.35
    Activations Density 0.000%

    No Known Activations