© 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. 138102
    Prev
    Next
    INDEX
    Explanations

    SEC

    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
     authority
    0.53
     Authority
    0.46
    Authority
    0.44
    authority
    0.43
     guise
    0.38
    =-\
    0.38
     autoridad
    0.38
    }}=-\
    0.38
    "+
    0.37
    }}$,
    0.37
    POSITIVE LOGITS
     मैनेजमेंट
    0.43
     Enrich
    0.39
    㽞
    0.39
    Dream
    0.38
    パック
    0.38
     एक्सपेक्ट
    0.38
     डिजा
    0.37
    MANAG
    0.37
    dream
    0.37
     publicly
    0.37
    Activations Density 0.001%

    No Known Activations