© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11615
    Prev
    Next
    INDEX
    Explanations

    the word "fight" and related words like "fights", "fighter", or "fought".

    oai_token-act-pair · gemini-2.0-flash

    fight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     fight
    -2.80
    fight
    -2.48
     fighting
    -2.38
     Fight
    -2.34
    Fight
    -2.27
     fights
    -2.20
     fought
    -2.20
     FIGHT
    -2.16
    fighting
    -2.11
    Fighting
    -2.03
    POSITIVE LOGITS
     cul
    0.49
    PageRoute
    0.46
    UDAD
    0.46
    kano
    0.45
    fficio
    0.44
    RISE
    0.43
    mentaux
    0.43
    adalajara
    0.42
    الإنجليزية
    0.42
    vium
    0.42
    Activations Density 0.948%

    No Known Activations