© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9431
    Prev
    Next
    INDEX
    Explanations

    text from legal documents

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     correctes
    -0.69
    PhysRevLett
    -0.56
    jface
    -0.55
    InSection
    -0.53
    detectChanges
    -0.53
    djangoproject
    -0.52
    HomeAsUpEnabled
    -0.52
     inoxydable
    -0.52
     exemplaires
    -0.50
     saites
    -0.50
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.71
     GenerationType
    0.52
     дописавши
    0.50
    PerformLayout
    0.49
    SpringBootTest
    0.48
    الإنجليزية
    0.47
    MigrationBuilder
    0.46
    LUM
    0.45
     Пло
    0.45
    '},
    0.44
    Activations Density 9.100%

    No Known Activations