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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4625
    Prev
    Next
    INDEX
    Explanations

    text about NFL football.

    oai_token-act-pair · gemini-2.0-flash

    Football

    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
     defense
    -1.40
     defence
    -1.35
    Defense
    -1.16
     Defense
    -1.14
    defense
    -1.10
     Defence
    -1.06
    Defence
    -1.06
     defensive
    -1.06
    Defensive
    -1.05
     DEFENSE
    -1.03
    POSITIVE LOGITS
     SqlCommand
    0.45
    ients
    0.45
     Perd
    0.44
    styleable
    0.43
    ViewImports
    0.43
    tamb
    0.41
    LElement
    0.40
    bets
    0.40
    ಲ್ಲ
    0.39
     MIND
    0.39
    Activations Density 3.441%

    No Known Activations