© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217305
    Prev
    Next
    INDEX
    Explanations

    ambitious

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    pers
    0.51
     pers
    0.42
     scrambling
    0.41
     নন্দ
    0.39
    一樣
    0.38
    蹿
    0.38
    สูงสุด
    0.37
    ﺻ
    0.37
    coder
    0.36
    adata
    0.36
    POSITIVE LOGITS
     Sebastian
    0.39
    backgroundSplit
    0.39
     aid
    0.38
    ционно
    0.38
     Edmund
    0.37
    ђе
    0.37
     bark
    0.37
     Chal
    0.37
     Bih
    0.36
     onClose
    0.36
    Activations Density 0.001%

    No Known Activations