© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8073
    Prev
    Next
    INDEX
    Explanations

    various letters, numbers, and punctuation used for formatting and abbreviations in different contexts like code, law, or data logs.

    oai_token-act-pair · gemini-2.0-flash

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.69
    me
    -0.45
    ver
    -0.42
    ze
    -0.41
    ite
    -0.40
     port
    -0.40
    wit
    -0.40
     me
    -0.40
     |
    -0.40
     –
    -0.39
    POSITIVE LOGITS
    contentLoaded
    1.01
     كومونز
    0.79
    تقاوى
    0.76
    expandindo
    0.75
     HasFactory
    0.75
     дописавши
    0.75
     Majefty
    0.73
     AttributeSet
    0.71
    Демографія
    0.71
     withal
    0.68
    Activations Density 1.554%

    No Known Activations