© 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. 51623
    Prev
    Next
    INDEX
    Explanations

    square root or backwards

    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
     celor
    0.16
     সম্পর্কিত
    0.16
     Geographic
    0.15
    둘
    0.15
     criticisms
    0.15
     outcomes
    0.15
     Sf
    0.15
     सिद्धांत
    0.15
    速
    0.15
     पुन
    0.14
    POSITIVE LOGITS
     আশায়
    0.19
    osyl
    0.17
     vẻ
    0.17
    宣言
    0.17
    कील
    0.16
    Cancer
    0.16
    宣告
    0.16
    鲳
    0.16
     mé
    0.16
    вій
    0.16
    Activations Density 0.000%

    No Known Activations