© 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. 1075
    Prev
    Next
    INDEX
    Explanations

    NY and related abbreviations

    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
    ೀತ
    0.42
    @{
    0.41
    BTN
    0.38
     Buffered
    0.36
    われています
    0.36
     মোত
    0.34
     coisa
    0.34
     Rout
    0.34
     fileobj
    0.33
     ^{\
    0.33
    POSITIVE LOGITS
     لمع
    0.42
    horizon
    0.40
    ালো
    0.40
    eV
    0.40
    ony
    0.39
    mvc
    0.37
    ekan
    0.37
     horizon
    0.37
     elektri
    0.36
    uny
    0.36
    Activations Density 0.017%

    No Known Activations