© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7522
    Prev
    Next
    INDEX
    Explanations

    the word "use"

    oai_token-act-pair · gemini-2.0-flash

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    )");
    -0.79
     ویکی‌پدیا
    -0.69
     kaarangay
    -0.67
    LookAnd
    -0.66
    }>;
    -0.65
    ArgsConstructor
    -0.64
    Kanpo
    -0.61
    تقاوى
    -0.61
    --)
    -0.60
    oa̍t
    -0.60
    POSITIVE LOGITS
    makeText
    0.55
     cases
    0.54
    GUILayout
    0.50
    GetEnumerator
    0.48
    cle
    0.45
     nõ
    0.44
    mitos
    0.44
    Serializable
    0.43
    Geografi
    0.43
     enqu
    0.43
    Activations Density 1.744%

    No Known Activations