© 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. 143213
    Prev
    Next
    INDEX
    Explanations

    US geography

    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
    芾
    0.41
     Heg
    0.40
     Mutable
    0.40
    舰
    0.38
     Joaquin
    0.38
     Maine
    0.38
    脏
    0.37
    浑
    0.37
     doğal
    0.37
     Farn
    0.37
    POSITIVE LOGITS
     caves
    0.45
     america
    0.40
    books
    0.40
     books
    0.40
    endem
    0.39
     Books
    0.39
    спо
    0.38
    ])/
    0.38
     cav
    0.37
    cad
    0.36
    Activations Density 0.000%

    No Known Activations