© 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. 3629
    Prev
    Next
    INDEX
    Explanations

    content from a variety of different topics

    oai_token-act-pair · gemini-2.0-flash

    professions

    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
     volunteer
    -0.88
     rival
    -0.83
     favourite
    -0.82
     favorite
    -0.81
    favourite
    -0.75
     variant
    -0.75
     giant
    -0.73
     mutant
    -0.73
    favorite
    -0.72
     representative
    -0.70
    POSITIVE LOGITS
     Teacher
    0.73
    Teacher
    0.68
     teacher
    0.65
    RunWith
    0.62
    teacher
    0.60
    multicolumn
    0.57
     Physician
    0.56
    父
    0.55
     Reinh
    0.55
     useAuth
    0.54
    Activations Density 4.000%

    No Known Activations