© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3685
    Prev
    Next
    INDEX
    Explanations

    various fragments of code, configuration files, and xml

    oai_token-act-pair · gemini-2.0-flash

    Code/technical formats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    BindingResult
    -0.57
    ApiProperty
    -0.54
     BoxFit
    -0.54
    StoryboardSegue
    -0.53
     BoxDecoration
    -0.51
     enää
    -0.50
    :])
    -0.49
    featureID
    -0.49
     découver
    -0.49
    ientôt
    -0.49
    POSITIVE LOGITS
    出版年
    0.68
    
    0.58
    ScopeManager
    0.57
     lò
    0.49
    queryInterface
    0.48
    inde
    0.47
    re
    0.47
     Seeder
    0.46
    Migration
    0.46
    MigrationBuilder
    0.46
    Activations Density 2.063%

    No Known Activations