© 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. 14724
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with legal and constitutional arguments and judgements.

    oai_token-act-pair · gemini-2.0-flash

    legal opinions and standards

    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
     שוליים
    -0.66
    хьтан
    -0.63
    IonicModule
    -0.62
    robial
    -0.55
    tioner
    -0.53
    日閲覧
    -0.53
    grà
    -0.53
    posedge
    -0.52
     saites
    -0.52
    uders
    -0.51
    POSITIVE LOGITS
     AssemblyProduct
    0.59
    AntiForgeryToken
    0.54
     froide
    0.52
    ViewChild
    0.52
     متعلقه
    0.52
     betweenstory
    0.50
    ApiOperation
    0.49
     Signalez
    0.49
     الحره
    0.47
    MoveNext
    0.45
    Activations Density 5.487%

    No Known Activations