© 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. 34560
    Prev
    Next
    INDEX
    Explanations

    correcting text

    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
    ّى
    0.39
    nev
    0.36
    ῇ
    0.36
     стаття
    0.35
    ႇ
    0.35
    াইল
    0.35
    ྱི་
    0.34
    allery
    0.34
    ّا
    0.34
    ilish
    0.34
    POSITIVE LOGITS
     जेसीबी
    0.38
    敵
    0.36
    கரு
    0.36
     waterfall
    0.35
    应用于
    0.35
    крови
    0.35
    wpilib
    0.34
     slowing
    0.34
     निकला
    0.34
    越来越多的
    0.34
    Activations Density 0.066%

    No Known Activations