© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245307
    Prev
    Next
    INDEX
    Explanations

    questions seeking explanation

    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_40_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
     según
    0.52
     according
    0.43
     Según
    0.43
    人の
    0.41
     propuesta
    0.39
     לפי
    0.39
    gest
    0.38
    <0x8B>
    0.38
    berto
    0.38
    according
    0.38
    POSITIVE LOGITS
     питання
    0.49
     вопроса
    0.48
     переписи
    0.43
     ব্যাকটেরিয়া
    0.40
     question
    0.38
    question
    0.38
    وْ
    0.37
     ചോദ്യ
    0.37
     질문
    0.37
    Ỡ
    0.37
    Activations Density 0.007%

    No Known Activations