© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15468
    Prev
    Next
    INDEX
    Explanations

    the letter 'K', sometimes preceded by 'C', and also the word 'discovers'

    oai_token-act-pair · gemini-2.0-flash

    K

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     K
    -1.46
    K
    -1.05
     К
    -0.80
     k
    -0.78
    Kx
    -0.71
     CURIAM
    -0.66
    Ｋ
    -0.65
    PhysRev
    -0.65
    Kt
    -0.63
     KC
    -0.62
    POSITIVE LOGITS
    ViewFeatures
    0.55
    king
    0.54
    XmlAccessType
    0.54
    ling
    0.53
     دیکھیے
    0.52
     TextAppearance
    0.52
     AssemblyProduct
    0.50
    adır
    0.50
    /*
    0.50
    SUND
    0.49
    Activations Density 0.233%

    No Known Activations