© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 322
    Prev
    Next
    INDEX
    Explanations

    jargon associated with legal documents

    oai_token-act-pair · gemini-2.0-flash

    legal, reports, scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personendaten
    -0.76
    RTEX
    -0.73
    elemField
    -0.70
     تضيفلها
    -0.70
    GEBURTSDATUM
    -0.70
     aikaa
    -0.70
    хьтан
    -0.68
     ligiloj
    -0.68
    protoimpl
    -0.68
    POSITIVE LOGITS
     Lc
    0.57
     Ll
    0.55
     li
    0.50
     ling
    0.48
     lig
    0.48
     Regu
    0.48
     Qar
    0.46
     Lel
    0.45
     Ofic
    0.45
     lan
    0.44
    Activations Density 29.679%

    No Known Activations