© 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. 2958
    Prev
    Next
    INDEX
    Explanations

    contentious or combative language in politics, economics, or personal relationships.

    oai_token-act-pair · gemini-2.0-flash

    negative sentiment/opposition

    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
     opposition
    -1.95
     counter
    -1.83
     oppose
    -1.79
     contra
    -1.77
     opposing
    -1.75
     opposes
    -1.71
    Opposition
    -1.68
     opposed
    -1.68
     Counter
    -1.66
     Opposition
    -1.65
    POSITIVE LOGITS
     InputDecoration
    0.59
    scriptcase
    0.50
     poveznice
    0.46
    Pfalz
    0.43
    pasti
    0.42
    onAttach
    0.42
    OpenHelper
    0.42
    Corp
    0.41
    日閲覧
    0.41
    قایناقلار
    0.40
    Activations Density 5.164%

    No Known Activations