© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11157
    Prev
    Next
    INDEX
    Explanations

    latex math symbols, especially 'k'

    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
    king
    -0.74
    kle
    -0.66
    k
    -0.66
    ks
    -0.64
    ker
    -0.60
    ked
    -0.59
    que
    -0.59
    ke
    -0.58
    ⓧ
    -0.58
    cok
    -0.57
    POSITIVE LOGITS
     K
    1.27
     К
    0.98
     KR
    0.90
     Κ
    0.90
     KT
    0.88
     KI
    0.86
     KU
    0.84
     KC
    0.83
     KP
    0.83
     KW
    0.82
    Activations Density 1.977%

    No Known Activations