© 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. 233580
    Prev
    Next
    INDEX
    Explanations

    characters

    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
     salmon
    0.41
    ท้อง
    0.40
    Salmon
    0.39
    Angela
    0.39
     વિધાનસભા
    0.38
     Salmon
    0.38
    俞
    0.36
     Chico
    0.35
    setShow
    0.35
     angular
    0.35
    POSITIVE LOGITS
     letters
    1.82
    字
    1.76
    字母
    1.73
     حروف
    1.73
     Buchstaben
    1.72
     huruf
    1.71
    letters
    1.67
     буквы
    1.63
     chữ
    1.62
     letras
    1.61
    Activations Density 0.002%

    No Known Activations