Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5673
    Prev
    Next
    INDEX
    Explanations

    words associated with political conspiracy theories and the far-right.

    oai_token-act-pair · gemini-2.0-flash

    anti-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Political, racial discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AndEndTag
    -0.84
     ſta
    -0.80
     ſtate
    -0.76
     myſelf
    -0.75
     quæ
    -0.70
     pleaſure
    -0.69
    انجليز
    -0.69
     itſelf
    -0.68
    CodedInputStream
    -0.67
     stiefel
    -0.66
    POSITIVE LOGITS
    MessageTagHelper
    0.57
    qtype
    0.54
    utilisons
    0.52
     "
    0.50
     anti
    0.49
     F
    0.48
     f
    0.47
    spě
    0.46
     kor
    0.44
     “
    0.44
    Activations Density 5.243%

    No Known Activations