© 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
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 119573
    Prev
    Next
    INDEX
    Explanations

    continuously doing something

    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_38_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
     propuestas
    0.40
    скай
    0.38
    স্ট
    0.38
    啷
    0.37
     dukkh
    0.37
    텟
    0.37
     sket
    0.36
    返回值
    0.36
     স্ক
    0.36
     proposals
    0.35
    POSITIVE LOGITS
    Mars
    0.38
    ೂರ್ವ
    0.38
     Ron
    0.38
     Frei
    0.38
    Ron
    0.36
    rends
    0.35
    Ports
    0.35
    appré
    0.35
     Ports
    0.35
    ջ
    0.35
    Activations Density 0.004%

    No Known Activations