© 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. 5739
    Prev
    Next
    INDEX
    Explanations

    text discussing presidents, especially in the context of the White House and related topics such as chefs and approval ratings.

    oai_token-act-pair · gemini-2.0-flash

    presidents

    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
     President
    -2.67
    President
    -2.56
     president
    -2.45
     PRESIDENT
    -2.33
     presidential
    -2.27
    president
    -2.19
     Presidential
    -2.16
    PRESIDENT
    -2.08
     presidents
    -2.02
     Presidents
    -1.98
    POSITIVE LOGITS
    AutoScale
    0.49
    ITÀ
    0.43
    EDEFAULT
    0.42
     colouring
    0.41
    dAtA
    0.40
    šk
    0.40
     khoe
    0.39
     NRK
    0.38
     vector
    0.38
    ובת
    0.38
    Activations Density 2.382%

    No Known Activations