© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4718
    Prev
    Next
    INDEX
    Explanations

    named entities and related context surrounding those entities.

    oai_token-act-pair · gemini-2.0-flash

    Place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Black
    -0.57
     Blood
    -0.57
     H
    -0.53
     chivalry
    -0.53
     La
    -0.49
     Gas
    -0.47
    vantaged
    -0.47
     M
    -0.46
    دید
    -0.46
     Poly
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.82
    RenderAtEndOf
    0.82
    parsedMessage
    0.81
    uxxxx
    0.76
     Мексичка
    0.76
     resourceCulture
    0.75
    Datuak
    0.69
    StructEnd
    0.69
    tableFuture
    0.69
    windowFixed
    0.69
    Activations Density 2.246%

    No Known Activations