© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 565
    Prev
    Next
    INDEX
    Explanations

    mentions of conflict, fighting, and adversity

    oai_token-act-pair · gemini-2.0-flash

    fight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -2.64
     fighting
    -2.56
     Fight
    -2.45
    fight
    -2.41
     FIGHT
    -2.34
     fights
    -2.33
    Fight
    -2.33
    Fighting
    -2.31
     Fighting
    -2.28
     fought
    -2.25
    POSITIVE LOGITS
    AndEndTag
    0.87
    日閲覧
    0.59
    FXML
    0.58
    Hauptartikel
    0.54
    SharedDtor
    0.52
    Portail
    0.52
    AccessorTable
    0.49
    AccessFile
    0.47
    
    0.47
     OnInit
    0.46
    Activations Density 2.235%

    No Known Activations