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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5237
    Prev
    Next
    INDEX
    Explanations

    names of people, especially attorneys and professors, along with legal citations

    oai_token-act-pair · gemini-2.0-flash

    Legal documents/names

    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
     سكانية
    -0.53
    InitVars
    -0.39
    IndentedString
    -0.38
     tartalomajánló
    -0.37
    MessageState
    -0.36
     تكبرها
    -0.36
    Personensuche
    -0.35
    abestanden
    -0.35
     himo
    -0.35
    tide
    -0.35
    POSITIVE LOGITS
     Scherer
    0.85
     Schmitz
    0.83
     Cline
    0.80
     Herrmann
    0.79
     Dodson
    0.78
     nationaux
    0.75
     Shoemaker
    0.75
    isRequired
    0.75
     Schroeder
    0.74
     Boyce
    0.73
    Activations Density 3.098%

    No Known Activations