© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177765
    Prev
    Next
    INDEX
    Explanations

    Wid

    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
    OfThe
    0.47
    ğaz
    0.41
    ogenes
    0.41
    anga
    0.39
    Determ
    0.39
    恝
    0.38
    стями
    0.38
     behe
    0.37
    ície
    0.37
    gena
    0.37
    POSITIVE LOGITS
    Nelson
    0.40
    }},
    0.40
     السنة
    0.39
    <0x9B>
    0.38
    Selenium
    0.38
    тим
    0.38
     selenium
    0.38
     normalmente
    0.38
     {,
    0.37
    selenium
    0.36
    Activations Density 0.001%

    No Known Activations