© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79285
    Prev
    Next
    INDEX
    Explanations

    geography and names

    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_53_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
    Gu
    0.45
    顾
    0.44
     गु
    0.42
     гу
    0.41
     হুমায়
    0.41
     ху
    0.41
     ጉ
    0.40
    tabs
    0.40
    mala
    0.40
    ើម
    0.39
    POSITIVE LOGITS
     Keystone
    0.52
     öt
    0.42
     түз
    0.42
     KE
    0.40
     ت
    0.40
     Ke
    0.40
     ke
    0.39
     t
    0.39
     Gad
    0.39
    Gad
    0.39
    Activations Density 0.001%

    No Known Activations