© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50495
    Prev
    Next
    INDEX
    Explanations

    purpose or aim

    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
     carries
    0.38
    塀
    0.37
    anın
    0.35
    حية
    0.35
    <0xBB>
    0.35
    <0xBE>
    0.34
    adol
    0.34
     tabPanel
    0.34
    <0xBF>
    0.34
    हीं
    0.34
    POSITIVE LOGITS
    希望能
    0.43
    希望
    0.43
    是为了
    0.42
     hoping
    0.42
     تاکہ
    0.42
     hope
    0.40
     hoped
    0.40
    意
    0.40
    why
    0.39
     כדי
    0.39
    Activations Density 0.008%

    No Known Activations