© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3624
    Prev
    Next
    INDEX
    Explanations

    language frequently used in legal documents

    oai_token-act-pair · gemini-2.0-flash

    legal disputes and rights

    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
     للمعارف
    -0.75
     autorytatywna
    -0.74
     AppCompatTheme
    -0.74
    LookAnd
    -0.74
     faced
    -0.73
     petitioned
    -0.70
    complexContent
    -0.70
     getItemId
    -0.68
    Personensuche
    -0.67
     sued
    -0.66
    POSITIVE LOGITS
    $__
    0.53
     recognised
    0.52
     recognized
    0.49
     Extragalactic
    0.49
     approved
    0.49
    COUVER
    0.47
    Pyx
    0.44
    DataAnnotations
    0.42
    UserScript
    0.42
     sanctioned
    0.40
    Activations Density 6.109%

    No Known Activations