© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200877
    Prev
    Next
    INDEX
    Explanations

    castling notation

    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_12_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
    Abroad
    0.55
    lbrakk
    0.52
    фикация
    0.51
     হইয়৷
    0.51
    Zd
    0.49
    pessoa
    0.48
    LOADING
    0.48
    Nota
    0.48
    Hazel
    0.48
    乀
    0.48
    POSITIVE LOGITS
    encher
    0.55
    も
    0.49
     આવ્યું
    0.48
     told
    0.48
     figurines
    0.48
    ancen
    0.48
    eture
    0.47
     apportion
    0.47
     ventes
    0.47
     medica
    0.46
    Activations Density 0.000%

    No Known Activations