© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6546
    Prev
    Next
    INDEX
    Explanations

    mentions of cultural venues and events and their locations

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    èlement
    -0.73
    ImageContext
    -0.65
     itſelf
    -0.64
     propOrder
    -0.63
    Статья
    -0.61
     <",
    -0.61
    //});
    -0.60
     getItemId
    -0.59
     himſelf
    -0.59
     gettyimages
    -0.59
    POSITIVE LOGITS
    IsContent
    0.56
    tagHelperRunner
    0.49
    sidemargin
    0.47
    smarty
    0.44
    JsonInclude
    0.44
    tein
    0.43
    EndContext
    0.43
    Rod
    0.42
    QG
    0.41
    MAC
    0.41
    Activations Density 1.199%

    No Known Activations