© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14381
    Prev
    Next
    INDEX
    Explanations

    court transcripts and related legal jargon.

    oai_token-act-pair · gemini-2.0-flash

    Legal transcripts

    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
     and
    -0.64
    fjspx
    -0.62
    TagMode
    -0.57
    AndGet
    -0.57
    Demografía
    -0.55
    RegistryLite
    -0.55
    autoIncrement
    -0.54
     surla
    -0.54
    MemoryWarning
    -0.53
     orphanage
    -0.52
    POSITIVE LOGITS
    Референце
    0.55
    AutoField
    0.52
    日閲覧
    0.51
     Lin
    0.51
    wußt
    0.50
     Gleaner
    0.50
    ladesh
    0.50
    ządz
    0.49
     To
    0.49
    Hozzáférés
    0.48
    Activations Density 17.087%

    No Known Activations