© 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. 197220
    Prev
    Next
    INDEX
    Explanations

    Detroit urban agriculture

    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
     οργαν
    0.39
     Par
    0.38
     Lid
    0.38
     oxidative
    0.37
    Alien
    0.37
     Yah
    0.37
     언
    0.36
    عم
    0.36
     Mati
    0.36
     নারায়ণ
    0.36
    POSITIVE LOGITS
    轱
    0.41
    woocommerce
    0.40
    ndale
    0.40
    Thomas
    0.39
     ഏക
    0.39
     trụ
    0.38
     recibirá
    0.38
    agar
    0.38
     thomas
    0.38
    anyl
    0.38
    Activations Density 0.000%

    No Known Activations