© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2491
    Prev
    Next
    INDEX
    Explanations

    code snippets and error messages

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.68
     élas
    -0.65
    ſelf
    -0.64
     Monfieur
    -0.63
    ſelves
    -0.62
     Theſe
    -0.58
    <bos>
    -0.57
    devším
    -0.57
     meantime
    -0.55
     meanwhile
    -0.54
    POSITIVE LOGITS
    MetaObject
    0.75
     typelib
    0.73
    zzleHttp
    0.69
    AndEndTag
    0.68
    makeText
    0.56
     跳转至
    0.56
    出版年
    0.54
    存于互联网档案馆
    0.53
    TestingModule
    0.53
     kund
    0.51
    Activations Density 2.390%

    No Known Activations