© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6193
    Prev
    Next
    INDEX
    Explanations

    the letter "K" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'K'

    np_token-act-pair-logits · gpt-4o-mini

    K

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    GOTREF
    -0.80
     autorytatywna
    -0.79
     AssemblyVersion
    -0.71
    EClass
    -0.70
     AssemblyTitle
    -0.69
    InputBorder
    -0.62
    ModelAdmin
    -0.59
    AutoScale
    -0.57
    FormTagHelper
    -0.57
    getFullYear
    -0.56
    POSITIVE LOGITS
     LUMP
    0.48
     ویکی‌پدیای
    0.47
    脚注の使い方
    0.46
    >${
    0.45
     locaux
    0.43
    ILayout
    0.42
    podar
    0.42
    туа
    0.40
    mazoo
    0.40
     harap
    0.40
    Activations Density 2.128%

    No Known Activations