© 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. 33372
    Prev
    Next
    INDEX
    Explanations

    per

    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
    ね
    0.39
     mimic
    0.38
    дыду
    0.38
    kaj
    0.38
    iol
    0.37
     अंग
    0.37
    級
    0.36
    ิก
    0.36
     ಹೋ
    0.36
    าง
    0.35
    POSITIVE LOGITS
     وج
    0.43
     Salvador
    0.42
    edor
    0.41
    apeti
    0.40
    wehr
    0.39
    ETC
    0.38
    atin
    0.38
    gri
    0.37
     Gri
    0.37
    urile
    0.37
    Activations Density 0.001%

    No Known Activations