© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8000
    Prev
    Next
    INDEX
    Explanations

    words related to problem solving and programming

    oai_token-act-pair · gemini-2.0-flash

    technical advice/help discussion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    OrCreate
    -0.49
    ئيس
    -0.47
     veille
    -0.46
     keberadaan
    -0.46
     adipis
    -0.43
     as
    -0.43
     toiminta
    -0.42
    clusão
    -0.42
     déclar
    -0.42
    áček
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.67
    endphp
    0.66
    Portale
    0.65
     recommendation
    0.57
    ệp
    0.56
    QApplication
    0.56
    HomeAsUpEnabled
    0.55
     Hopf
    0.55
     Doi
    0.55
     suggestion
    0.54
    Activations Density 1.287%

    No Known Activations