© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15624
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags or attributes with numeric values

    oai_token-act-pair · gemini-2.0-flash

    code and numeric values

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.68
    zow
    -0.63
    fxml
    -0.59
    ofag
    -0.59
    发表于
    -0.59
    enumi
    -0.57
    prepareStatement
    -0.56
    #+#
    -0.56
     Mor
    -0.56
     Rest
    -0.56
    POSITIVE LOGITS
    <bos>
    0.95
    '
    0.74
     newBuilder
    0.73
     vectorielle
    0.68
     Monfieur
    0.63
     nostru
    0.63
     avoient
    0.63
     vectorielles
    0.61
    principalTable
    0.61
     étoit
    0.61
    Activations Density 8.292%

    No Known Activations