© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63485
    Prev
    Next
    INDEX
    Explanations

    complex decisions

    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_46_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
     Aper
    0.40
    ;\
    0.38
    ]]]
    0.38
    "=>$
    0.38
    "\
    0.37
    inging
    0.37
    ního
    0.36
    กรา
    0.36
     Cafe
    0.36
    lice
    0.36
    POSITIVE LOGITS
     ஜனநாயக
    0.38
    ]<?
    0.37
    outi
    0.36
    പക്ഷ
    0.35
    encana
    0.35
    ıklı
    0.35
    ट
    0.35
    Cliff
    0.35
    ritic
    0.34
     niz
    0.34
    Activations Density 0.094%

    No Known Activations