© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10923
    Prev
    Next
    INDEX
    Explanations

    references connected to organizations, locations, government, and committees

    oai_token-act-pair · gemini-2.0-flash

    old texts/foreign names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     détru
    -0.47
     déchir
    -0.47
     stället
    -0.46
     démocr
    -0.45
     cœurs
    -0.44
     supérieurs
    -0.44
     négociations
    -0.43
     pauvres
    -0.43
     prisonniers
    -0.42
     colorés
    -0.42
    POSITIVE LOGITS
     Cæsar
    0.67
     Shakspeare
    0.63
     Shaksp
    0.54
     Pliny
    0.53
     Houſe
    0.52
     Phry
    0.50
     Monfieur
    0.50
     Thebes
    0.49
     Anſ
    0.49
     Diſ
    0.48
    Activations Density 26.787%

    No Known Activations