© 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. 2011
    Prev
    Next
    INDEX
    Explanations

    complicated legal language, particularly citing court cases and legal precedence.

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks / parenthesis

    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
    I
    -0.47
    IKAN
    -0.45
    th
    -0.43
    many
    -0.43
    light
    -0.42
    removeChild
    -0.41
    zema
    -0.40
    most
    -0.40
    this
    -0.40
    ≦)
    -0.39
    POSITIVE LOGITS
    ArgsConstructor
    1.03
     Roskov
    0.90
     betweenstory
    0.89
     виправивши
    0.73
    AutoField
    0.72
     للمعارف
    0.68
    fromnode
    0.67
    DockStyle
    0.67
     '\\;'
    0.67
    DeleteBehavior
    0.66
    Activations Density 6.723%

    No Known Activations