© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12973
    Prev
    Next
    INDEX
    Explanations

    language expressing the dependence of one entity on another

    oai_token-act-pair · gemini-2.0-flash

    advertisements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    tagHelperRunner
    -0.63
    ">//
    -0.56
    IntoConstraints
    -0.53
     piede
    -0.47
    Aholisi
    -0.46
    akat
    -0.44
    EndInit
    -0.44
     Baillargeon
    -0.41
    routeProvider
    -0.41
     Alpes
    -0.40
    POSITIVE LOGITS
     ad
    2.36
     Ad
    1.59
    Ad
    1.50
    ad
    1.30
     ads
    0.99
     advert
    0.95
     AD
    0.94
     Ads
    0.92
    Ads
    0.86
     adu
    0.82
    Activations Density 4.643%

    No Known Activations