© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65736
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    号
    0.41
    விர
    0.38
    澼
    0.38
    talking
    0.37
    惮
    0.35
    ская
    0.34
     enlarge
    0.34
    correlated
    0.33
    unca
    0.33
    號
    0.33
    POSITIVE LOGITS
     산업
    0.47
     Neon
    0.44
     neon
    0.44
    neon
    0.38
     Carbon
    0.37
    Neon
    0.37
    Wallpaper
    0.35
     potre
    0.33
     შეგიძლიათ
    0.33
    ਣ
    0.33
    Activations Density 0.000%

    No Known Activations