© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11557
    Prev
    Next
    INDEX
    Explanations

    words related to fantasy, science fiction, and religion

    oai_token-act-pair · gemini-2.0-flash

    Imaginary/alternate worlds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     lèvres
    -0.63
     épaules
    -0.61
     prisonniers
    -0.58
     preuves
    -0.56
     man
    -0.54
    ratto
    -0.53
     négociations
    -0.53
     Juifs
    -0.52
     générations
    -0.52
     complémentaires
    -0.52
    POSITIVE LOGITS
    ThemeOverlay
    0.77
     виправивши
    0.71
     wives
    0.70
     places
    0.69
     earths
    0.68
     bikes
    0.68
     Meksiku
    0.67
    
    0.67
     nights
    0.66
     births
    0.65
    Activations Density 4.531%

    No Known Activations