© 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. 15430
    Prev
    Next
    INDEX
    Explanations

    the word "tears" and proper nouns

    oai_token-act-pair · gemini-2.0-flash

    tears

    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
     CALIFORNI
    -0.85
    .}(
    -0.82
    xffffffff
    -0.82
     ProductService
    -0.80
    ysing
    -0.80
     Vapour
    -0.79
     Cham
    -0.78
    **:
    -0.77
    merz
    -0.77
    limard
    -0.76
    POSITIVE LOGITS
    <bos>
    2.19
    ↵↵
    1.23
    ↵
    1.00
    '
    0.79
    ’
    0.64
     and
    0.63
      
    0.61
    A
    0.59
    I
    0.57
     The
    0.57
    Activations Density 1.373%

    No Known Activations