© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9608
    Prev
    Next
    INDEX
    Explanations

    various uses of the word "boundary" in different contexts, sometimes also picking up on similarly related but less strong matches

    oai_token-act-pair · gemini-2.0-flash

    boundary

    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
     Sociales
    -0.61
     récomp
    -0.58
     prefeitura
    -0.57
     couvert
    -0.57
    外部リンク
    -0.57
     paroisse
    -0.57
     trilha
    -0.56
     pédagogique
    -0.56
     recul
    -0.56
     exécut
    -0.56
    POSITIVE LOGITS
    )";
    0.87
    writeFieldEnd
    0.83
    .",
    0.80
    )");
    0.75
    .";
    0.75
     nahilalakip
    0.71
    leſs
    0.69
     (…)
    0.68
    ímite
    0.66
    .")]
    0.66
    Activations Density 1.751%

    No Known Activations