© 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. 249611
    Prev
    Next
    INDEX
    Explanations

    zero or 0

    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
     zero
    3.77
     Zero
    3.55
    Zero
    3.52
    zero
    3.31
     ZERO
    3.27
    零
    3.17
    ZERO
    3.11
     zéro
    2.95
    ゼロ
    2.92
     जीरो
    2.91
    POSITIVE LOGITS
    لع
    0.39
     Rahe
    0.37
    滌
    0.36
    निमल
    0.36
    ThreadPool
    0.34
    朼
    0.33
     Nizam
    0.33
     Duk
    0.33
     ലെ
    0.33
    στο
    0.32
    Activations Density 0.071%

    No Known Activations