© 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. 7743
    Prev
    Next
    INDEX
    Explanations

    content from legal documents and questions about physics

    oai_token-act-pair · gemini-2.0-flash

    science and engineering

    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
     administration
    -0.56
    Vidite
    -0.50
     Administration
    -0.48
     Consensus
    -0.47
    QMetaType
    -0.47
     Lordships
    -0.45
     ELD
    -0.44
    hosp
    -0.44
    日閲覧
    -0.44
    الحياه
    -0.43
    POSITIVE LOGITS
     vertically
    0.57
     horizontally
    0.55
     Exacts
    0.54
     tangential
    0.53
     $_{
    0.50
     propeller
    0.50
     instantaneously
    0.49
     $|
    0.49
    dzić
    0.49
     raggi
    0.49
    Activations Density 21.781%

    No Known Activations