© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5897
    Prev
    Next
    INDEX
    Explanations

    court proceedings, criminal charges, and legal terms

    oai_token-act-pair · gemini-2.0-flash

    legal convictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.30
     vectorielle
    -0.62
    ChildScrollView
    -0.58
    Билгалдахарш
    -0.56
     ſtand
    -0.54
     juſt
    -0.54
     purpoſe
    -0.52
     pleaſure
    -0.52
     faſt
    -0.52
     ainfi
    -0.51
    POSITIVE LOGITS
    addCriterion
    0.62
    ]='\
    0.61
    AnchorTagHelper
    0.60
    merie
    0.60
    OrBuilder
    0.57
     joaat
    0.56
    嘩
    0.55
    utory
    0.54
    Prosec
    0.54
    Criminal
    0.53
    Activations Density 4.030%

    No Known Activations