© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6103
    Prev
    Next
    INDEX
    Explanations

    the word "use" and words associated with usage and utility

    oai_token-act-pair · gemini-2.0-flash

    the word 'use' and its variations

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

    use

    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
     use
    -0.73
    use
    -0.57
    Use
    -0.57
     Waray
    -0.57
    USE
    -0.55
     USE
    -0.55
    用了
    -0.54
     Use
    -0.54
    used
    -0.53
    using
    -0.53
    POSITIVE LOGITS
    full
    0.74
    FormTagHelper
    0.72
    AndEndTag
    0.70
    FULL
    0.63
    fully
    0.63
    tative
    0.59
    FUL
    0.59
    printStackTrace
    0.58
    Full
    0.56
    フル
    0.56
    Activations Density 3.364%

    No Known Activations