© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10915
    Prev
    Next
    INDEX
    Explanations

    instances of someone thinking or hoping

    oai_token-act-pair · gemini-2.0-flash

    thought and belief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Gilla
    -0.50
     arbeids
    -0.42
     läs
    -0.41
    président
    -0.41
     détaillé
    -0.40
     Catawiki
    -0.40
    FXMLLoader
    -0.39
     tră
    -0.38
     îna
    -0.38
    !=
    -0.38
    POSITIVE LOGITS
    таратура
    0.82
    
    0.72
     tartalomajánló
    0.68
    TestingModule
    0.64
     estekak
    0.64
     متعلقه
    0.64
     Ressource
    0.63
    TIMORE
    0.63
     للاسماء
    0.60
    IsMutable
    0.60
    Activations Density 0.273%

    No Known Activations