© 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. 198627
    Prev
    Next
    INDEX
    Explanations

    okay, I

    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
    ListPage
    0.36
     깊
    0.36
     malades
    0.36
    মোহ
    0.35
     नाश
    0.35
     뉴
    0.35
     নিউ
    0.34
     آج
    0.34
     новогод
    0.34
     അല്ല
    0.33
    POSITIVE LOGITS
     meines
    0.42
     Tres
    0.42
    Tres
    0.40
     faccio
    0.38
    HashMap
    0.38
     Ere
    0.38
     CHO
    0.38
    梵
    0.38
     bb
    0.37
    亢
    0.37
    Activations Density 0.016%

    No Known Activations