© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50874
    Prev
    Next
    INDEX
    Explanations

    London places

    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_55_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
     postal
    0.41
    मंदिर
    0.41
     pal
    0.39
     inadmissible
    0.38
     ഒരു
    0.38
    frontal
    0.38
     ঢাকায়
    0.38
    宮
    0.37
    Franklin
    0.37
     пала
    0.37
    POSITIVE LOGITS
     Salts
    0.42
     Number
    0.41
     number
    0.40
    ią
    0.39
     olor
    0.39
     broj
    0.38
     Inglaterra
    0.38
     იქ
    0.38
    Number
    0.37
     Britain
    0.36
    Activations Density 0.004%

    No Known Activations