© 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. 178335
    Prev
    Next
    INDEX
    Explanations

    Greg

    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
     allotment
    0.41
     symbolically
    0.41
     Cel
    0.39
    नेक
    0.39
    нский
    0.39
     BONDS
    0.38
    珊瑚
    0.38
    펠
    0.38
     symbolic
    0.38
     allotments
    0.38
    POSITIVE LOGITS
    ento
    0.41
    खी
    0.39
    hasa
    0.38
    ossos
    0.37
    EOS
    0.37
    znym
    0.37
    يطان
    0.37
    enture
    0.36
    Hou
    0.36
    hou
    0.36
    Activations Density 0.000%

    No Known Activations