© 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. 9807
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to genes, proteins, medical conditions, research studies and political conflict

    oai_token-act-pair · gemini-2.0-flash

    Technical/medical studies

    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
    an
    -0.76
    al
    -0.69
    by
    -0.68
    StoryboardSegue
    -0.64
    PageRoute
    -0.57
    YourGuide
    -0.57
    alva
    -0.52
    er
    -0.50
    ChildIndex
    -0.49
    ian
    -0.49
    POSITIVE LOGITS
     noires
    0.56
    retweeted
    0.56
     gyhoeddwyd
    0.54
    gather
    0.52
    SharedCtor
    0.50
    hos
    0.50
    hom
    0.49
    hards
    0.48
    interopRequire
    0.48
    homonymie
    0.48
    Activations Density 9.414%

    No Known Activations