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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14628
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings and money

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     bezeichneter
    -0.59
    Datuak
    -0.56
    ']").
    -0.52
     виправивши
    -0.52
    \"");
    -0.50
     فريبيس
    -0.49
    ńst
    -0.49
    complexType
    -0.47
    "]').
    -0.47
    <bos>
    -0.47
    POSITIVE LOGITS
     ligiloj
    0.66
    UIControlState
    0.64
    TypedDataSet
    0.63
     esternos
    0.60
    nonatomic
    0.59
    Биография
    0.58
     handleMessage
    0.55
    élien
    0.54
     الرياضيه
    0.53
    ánto
    0.52
    Activations Density 7.570%

    No Known Activations