© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32269
    Prev
    Next
    INDEX
    Explanations

    all languages

    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
    гот
    0.39
     Пав
    0.39
     declines
    0.37
     জিনিস
    0.36
     πλη
    0.36
     percentuale
    0.36
     син
    0.35
    嬿
    0.35
     فا
    0.35
     scrapes
    0.35
    POSITIVE LOGITS
     Cũng
    0.43
    ajući
    0.42
    Also
    0.41
     Lo
    0.40
     AES
    0.40
    ವೂ
    0.40
    টাও
    0.40
     Also
    0.40
     also
    0.39
    কেও
    0.39
    Activations Density 0.009%

    No Known Activations