© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 386
    Prev
    Next
    INDEX
    Explanations

    numerical values, including numbers written out as words

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Drapeau
    -0.82
     SafeMath
    -0.70
    didSet
    -0.65
     eventdata
    -0.62
    MessageOf
    -0.62
    SPATH
    -0.60
     &___
    -0.59
     megfe
    -0.59
    neté
    -0.59
     Gattung
    -0.57
    POSITIVE LOGITS
    <bos>
    0.68
     CreateTagHelper
    0.63
    >(_
    0.58
    eratops
    0.57
    ])));
    0.57
    ']));
    0.56
     sta
    0.55
    "]));
    0.54
    ]));
    0.53
     *>(
    0.52
    Activations Density 4.119%

    No Known Activations