© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6893
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or names, places, and organizations associated with the color blue or white

    oai_token-act-pair · gemini-2.0-flash

    White House

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ValueGeneration
    -0.74
    rungsseite
    -0.71
     cherchés
    -0.66
     betweenstory
    -0.66
    djangoproject
    -0.63
    LinkId
    -0.62
    tagHelperRunner
    -0.61
     lenker
    -0.61
    UrlResolution
    -0.61
    RetentionPolicy
    -0.60
    POSITIVE LOGITS
    heath
    0.48
     Jackets
    0.47
     Owls
    0.46
    Birch
    0.46
     arşivlendi
    0.46
     Spruce
    0.46
     Whip
    0.45
     rêver
    0.45
     Fern
    0.45
    GroupLayout
    0.45
    Activations Density 4.132%

    No Known Activations