© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51814
    Prev
    Next
    INDEX
    Explanations

    when you run it

    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_30_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
     دون
    0.39
     முதல்
    0.38
    가는
    0.37
     waarbij
    0.37
    design
    0.37
    利
    0.37
    AMERICAN
    0.35
    ⸱
    0.35
     evidencia
    0.35
     design
    0.34
    POSITIVE LOGITS
     इसको
    0.40
    พวกเขา
    0.38
     you
    0.36
    你会
    0.36
     grasped
    0.36
     তাঁরা
    0.34
     they
    0.34
    Flow
    0.33
     scolded
    0.33
     surprising
    0.33
    Activations Density 0.008%

    No Known Activations