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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 345
    Prev
    Next
    INDEX
    Explanations

    technical language in genetics research papers

    oai_token-act-pair · gemini-2.0-flash

    scientific text

    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
    expandindo
    -0.50
    standers
    -0.44
    ště
    -0.43
     realizing
    -0.43
     Пусть
    -0.42
    rancy
    -0.42
     appelez
    -0.42
    gerea
    -0.42
     experimenting
    -0.41
    ])));
    -0.41
    POSITIVE LOGITS
    #![
    0.75
    GeneratedMessage
    0.75
    rawDesc
    0.66
     SafeMath
    0.64
     VIAF
    0.64
     pinulongan
    0.63
    interopRequire
    0.61
    esModule
    0.60
    ResumeLayout
    0.60
    twimg
    0.60
    Activations Density 13.821%

    No Known Activations