© 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. 141078
    Prev
    Next
    INDEX
    Explanations

    Monaco

    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
     দিয়
    0.40
    カリ
    0.39
     получать
    0.38
    বত
    0.38
    RuL
    0.37
     ৭৫
    0.37
     importing
    0.36
    銛
    0.36
    xii
    0.36
    ২৪
    0.35
    POSITIVE LOGITS
    Important
    0.46
     tasted
    0.45
     T
    0.42
     goût
    0.42
     N
    0.41
    ITÉ
    0.40
     Clair
    0.40
     Confucian
    0.40
    IAC
    0.39
    countable
    0.38
    Activations Density 0.001%

    No Known Activations