© 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. 9359
    Prev
    Next
    INDEX
    Explanations

    the words "to" and "not" and personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     imprimée
    -0.67
     médicaux
    -0.66
     isolé
    -0.65
     RIPRODUZIONE
    -0.64
     exécu
    -0.64
    processes
    -0.64
     roulant
    -0.63
     promozione
    -0.63
     quæ
    -0.63
     alimentaires
    -0.63
    POSITIVE LOGITS
    RequiresApi
    0.57
     {}),
    0.57
    odoo
    0.56
    GeoNames
    0.56
     onCreateView
    0.55
    epar
    0.54
     NSCoder
    0.53
     {})
    0.51
    ForValue
    0.49
    ictwo
    0.49
    Activations Density 10.468%

    No Known Activations