© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2669
    Prev
    Next
    INDEX
    Explanations

    words expressing positive qualities or characteristics

    oai_token-act-pair · gemini-2.0-flash

    conjunctions and linking words

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

    "and" in different languages

    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
    
    -0.91
    DoubleQuotes
    -0.88
     ExecuteAsync
    -0.85
    __(/*!
    -0.82
    )");
    -0.80
    medriver
    -0.79
     endwhile
    -0.75
    ConstraintMaker
    -0.74
    strix
    -0.73
    queryInterface
    -0.72
    POSITIVE LOGITS
     and
    1.79
     &
    1.02
    และ
    0.86
     и
    0.85
     \&
    0.81
    ,
    0.81
     ומ
    0.75
     एवं
    0.73
    and
    0.72
     및
    0.71
    Activations Density 1.853%

    No Known Activations