© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    discourse markers that enumerate points or present contrasting ideas

    oai_token-act-pair · gemini-2.0-flash

    contrasting viewpoints

    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
     also
    -0.78
    あとは
    -0.66
    rigkeit
    -0.63
     также
    -0.56
     likewise
    -0.55
    MatInputModule
    -0.55
    popd
    -0.54
     anche
    -0.53
     accompaniment
    -0.52
     afterwards
    -0.52
    POSITIVE LOGITS
    存于互联网档案馆
    0.63
    ConstraintMaker
    0.61
    ագրություններ
    0.59
    DebuggerNonUser
    0.58
    Composable
    0.57
    ReusableCell
    0.56
    protoimpl
    0.54
    цездатний
    0.52
    তথ্যসূত্র
    0.52
    principalColumn
    0.52
    Activations Density 8.911%

    No Known Activations