© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11832
    Prev
    Next
    INDEX
    Explanations

    the word "childhood"

    oai_token-act-pair · gemini-2.0-flash

    childhood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     childhood
    -1.08
     Childhood
    -0.88
     boyhood
    -0.75
    Childhood
    -0.74
     Kindheit
    -0.71
     lifetime
    -0.69
    ']],
    -0.67
    ()");
    -0.66
    lifetime
    -0.65
     ();
    -0.63
    POSITIVE LOGITS
    <bos>
    0.79
    kkue
    0.66
    évaluateur
    0.61
    Morfologia
    0.53
     disambiguazione
    0.52
     Italijani
    0.52
    ագրություններ
    0.52
    gulation
    0.51
    पया
    0.50
    grà
    0.50
    Activations Density 1.743%

    No Known Activations