© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 5971
    Prev
    Next
    INDEX
    Explanations

    shitposter or out there

    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
    ಎಂ
    0.41
    하이
    0.39
     చరిత్ర
    0.39
    Xaml
    0.38
     Alright
    0.37
    Alright
    0.36
     dictated
    0.35
    桅
    0.35
     başlı
    0.35
    下滑
    0.35
    POSITIVE LOGITS
    takes
    0.42
     shum
    0.40
     tốc
    0.39
     î
    0.39
    ake
    0.38
     Khand
    0.38
     s
    0.38
    โซ
    0.38
     sows
    0.38
    zeich
    0.38
    Activations Density 0.045%

    No Known Activations