© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 34013
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
     DR
    0.41
    ಸೂ
    0.40
    𝐜
    0.39
    Leng
    0.37
    dR
    0.36
     bere
    0.36
    শনে
    0.36
    щини
    0.36
    atsiya
    0.36
     श्रद्धा
    0.35
    POSITIVE LOGITS
    ithe
    0.41
    湟
    0.41
     Karma
    0.40
     KAR
    0.39
     кара
    0.39
     toer
    0.38
    云南
    0.38
     vibration
    0.37
     মাল
    0.37
    Kar
    0.37
    Activations Density 0.012%

    No Known Activations