© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10865
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court proceedings, motions, and appeals

    oai_token-act-pair · gemini-2.0-flash

    motion

    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
    mereka
    -0.62
     wikipagina
    -0.59
     näky
    -0.59
     automatiques
    -0.59
     függ
    -0.56
     purpoſe
    -0.55
     chrétien
    -0.53
     světě
    -0.51
     ricevere
    -0.51
     originais
    -0.51
    POSITIVE LOGITS
     CURIAM
    1.10
     kasarigan
    0.81
    ANDUM
    0.81
     facie
    0.77
    TagMode
    0.77
    MEMORANDUM
    0.76
    CodedInputStream
    0.76
    fjspx
    0.75
     EClass
    0.73
    enterOuterAlt
    0.65
    Activations Density 3.571%

    No Known Activations