© 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. 9240
    Prev
    Next
    INDEX
    Explanations

    NVIDIA RTX 3090

    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
    六年
    0.45
     Six
    0.43
     tiek
    0.43
    ၆
    0.40
     nirv
    0.40
     Inicial
    0.39
     छठी
    0.38
     Sixth
    0.38
     ছয়
    0.38
     шесть
    0.38
    POSITIVE LOGITS
    3
    0.52
    9
    0.50
    
    0.46
    8
    0.44
    ۳
    0.43
    ૩
    0.41
    ३
    0.40
    ３
    0.39
    ９
    0.38
    Algorithms
    0.38
    Activations Density 0.048%

    No Known Activations