© 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. 64051
    Prev
    Next
    INDEX
    Explanations

    cities

    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
     Hedge
    0.47
    hedge
    0.47
    佉
    0.45
    سرائيل
    0.41
     காற்று
    0.39
     hedge
    0.38
    髏
    0.38
     nv
    0.37
    levi
    0.37
     Quotient
    0.36
    POSITIVE LOGITS
     서울
    1.41
     تهران
    1.34
    서울
    1.31
    東京
    1.29
     Budapest
    1.28
     Prague
    1.27
     कोलकाता
    1.27
     Vienna
    1.25
     Bangkok
    1.24
     Frankfurt
    1.24
    Activations Density 0.030%

    No Known Activations