© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2909
    Prev
    Next
    INDEX
    Explanations

    the word "fire," sometimes in the context of medicine or other elements but always "fire"

    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
    Negative Logits
    ↵↵
    -0.84
    ↵
    -0.51
    .
    -0.49
    ,
    -0.47
    FWIW
    -0.46
     res
    -0.45
     wüns
    -0.45
    <eos>
    -0.43
    ’
    -0.43
     somewhere
    -0.43
    POSITIVE LOGITS
     avoient
    0.94
     étoient
    0.94
     étoit
    0.94
     auroit
    0.89
    enumii
    0.79
     eût
    0.79
     suivie
    0.79
     humeur
    0.78
     feroit
    0.78
     ouvriers
    0.77
    Activations Density 1.190%

    No Known Activations