© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    tokens that are followed or preceded by auxiliary verbs.

    oai_token-act-pair · gemini-2.0-flash

    Actions or considerations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    PageModule
    -0.50
    ReactDOM
    -0.45
     per
    -0.45
    detectChanges
    -0.45
    rer
    -0.44
    pondi
    -0.43
    '
    -0.43
    getElementById
    -0.42
    sein
    -0.41
     hatır
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.64
    tvguidetime
    0.63
     insuffisamment
    0.61
    loit
    0.60
    EndInit
    0.59
    AutoScaleMode
    0.59
     Audiodateien
    0.59
    rawDesc
    0.58
    +:+
    0.57
     CreateTagHelper
    0.57
    Activations Density 1.369%

    No Known Activations