© 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. 13912
    Prev
    Next
    INDEX
    Explanations

    words associated with scientific findings or logical consequences

    oai_token-act-pair · gemini-2.0-flash

    correspond

    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
    <bos>
    -2.16
    '
    -0.66
    "
    -0.50
    ↵↵
    -0.49
     '<?
    -0.45
    ’
    -0.45
    <strong>
    -0.44
    e
    -0.43
    OGND
    -0.43
     måned
    -0.41
    POSITIVE LOGITS
    numerusform
    1.05
    ReusableCell
    0.73
     therefore
    0.72
    ArgsConstructor
    0.69
     pylint
    0.69
     accordingly
    0.65
    AxisAlignment
    0.64
     especially
    0.63
    存于互联网档案馆
    0.62
    tvguidetime
    0.61
    Activations Density 5.290%

    No Known Activations