© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50497
    Prev
    Next
    INDEX
    Explanations

    numbers near equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     قدیمی
    0.34
    リスク
    0.34
    ancel
    0.33
    path
    0.33
    엷
    0.33
    ready
    0.33
    ኡ
    0.33
    युक्त
    0.32
    inference
    0.32
     concerto
    0.32
    POSITIVE LOGITS
     এইসব
    0.38
    糖
    0.37
     moonlight
    0.36
     Tag
    0.35
     جغ
    0.35
     récemment
    0.35
     વચ્ચે
    0.35
    แถ
    0.35
    ₲
    0.35
     Thor
    0.35
    Activations Density 0.070%

    No Known Activations