© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 990
    Prev
    Next
    INDEX
    Explanations

    instances of k followed by digits or code related terms like klass, cfg, fmt, hk, and symbol

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -1.88
     k
    -1.84
    K
    -1.21
     K
    -1.13
     к
    -0.84
    𝙠
    -0.79
    𝐤
    -0.79
    𝘬
    -0.77
    К
    -0.77
     kink
    -0.77
    POSITIVE LOGITS
    Abitanti
    0.52
    ycznej
    0.47
    grà
    0.46
    ybė
    0.46
    ąd
    0.45
    Enllaços
    0.44
    tivität
    0.44
    робі
    0.44
    sschule
    0.44
     gorg
    0.44
    Activations Density 3.089%

    No Known Activations