© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130003
    Prev
    Next
    INDEX
    Explanations

    programming imports

    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_50_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
    แฟ
    0.36
    radi
    0.35
    )|$(
    0.35
    Willow
    0.35
    રી
    0.34
     monograph
    0.34
    Who
    0.33
    जे
    0.33
    geon
    0.33
    ଲା
    0.33
    POSITIVE LOGITS
    CLC
    0.45
    䈉
    0.43
     Kombat
    0.42
     Kazakhstan
    0.42
     Anambra
    0.41
     Ramadan
    0.40
    ற்புத
    0.40
    दाय
    0.40
     asynchronous
    0.39
     Ramirez
    0.39
    Activations Density 0.000%

    No Known Activations