© 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. 10392
    Prev
    Next
    INDEX
    Explanations

    the word "fire" in a variety of contexts, often related to actual fires or the act of firing someone.

    oai_token-act-pair · gemini-2.0-flash

    fire

    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
     him
    -0.69
    UVWXYZ
    -0.69
     perla
    -0.67
     ब्रेकडाउन
    -0.66
    ibatis
    -0.66
    roupe
    -0.65
    englanniksi
    -0.64
    moiselle
    -0.64
    kusen
    -0.63
     עליו
    -0.63
    POSITIVE LOGITS
    ReusableCell
    0.67
    verwijspagina
    0.65
    +#+#
    0.62
    ImageContext
    0.61
    LookAnd
    0.59
    >
    0.59
    StoryboardSegue
    0.59
    ↵↵
    0.58
    >);
    0.58
    ]){
    0.58
    Activations Density 2.139%

    No Known Activations