© 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. 8406
    Prev
    Next
    INDEX
    Explanations

    references to political figures and organizations

    oai_token-act-pair · gemini-2.0-flash

    Organizations and governments

    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
    AndEndTag
    -0.76
    fromnode
    -0.71
     دیکھیے
    -0.70
    :✨
    -0.68
    kloped
    -0.60
     <<<<<<<<<<<<<<
    -0.56
     мәкал
    -0.54
    spaceBetween
    -0.53
     surla
    -0.52
    oredCriteria
    -0.50
    POSITIVE LOGITS
     Houſe
    0.58
     fails
    0.54
     veneta
    0.51
     tangerang
    0.50
     Oeste
    0.49
    nimmt
    0.49
     commerciali
    0.48
     industriels
    0.48
     originali
    0.47
     Verdad
    0.46
    Activations Density 2.426%

    No Known Activations