© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15740
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and names of people.

    oai_token-act-pair · gemini-2.0-flash

    Names and quotes

    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
     have
    -0.81
     do
    -0.81
    ANTLR
    -0.78
     leaves
    -0.73
     raised
    -0.73
     paid
    -0.71
     spent
    -0.71
     lived
    -0.71
     repaid
    -0.70
    dymyr
    -0.70
    POSITIVE LOGITS
     réguli
    0.41
    WebElementEntity
    0.40
     aéro
    0.39
     nationaux
    0.39
     alvor
    0.38
     bienfaits
    0.38
     welkom
    0.38
     culturelles
    0.38
     stratégies
    0.38
     själ
    0.38
    Activations Density 9.146%

    No Known Activations