© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79683
    Prev
    Next
    INDEX
    Explanations

    urban walkable pedestrian zones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    능
    0.38
     campuses
    0.37
    Campus
    0.37
     नेक्स्ट
    0.36
     ngOnInit
    0.35
    络
    0.35
     الوزن
    0.35
    KeyPair
    0.35
    瀆
    0.35
    city
    0.34
    POSITIVE LOGITS
     Yel
    0.36
    ភ
    0.36
     Funded
    0.35
     SimSun
    0.34
     EH
    0.34
     yena
    0.34
     তুই
    0.34
     Bho
    0.34
    ারা
    0.34
     gowns
    0.33
    Activations Density 0.003%

    No Known Activations