© 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. 13932
    Prev
    Next
    INDEX
    Explanations

    prepositions and common short words used as function words, not content words, within a sentence.

    oai_token-act-pair · gemini-2.0-flash

    in

    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
     juridiques
    -0.64
     chré
    -0.62
     démocr
    -0.61
     grève
    -0.59
     étoient
    -0.59
     avoient
    -0.59
     marquées
    -0.58
     preghiera
    -0.55
     quantités
    -0.55
     ouverts
    -0.55
    POSITIVE LOGITS
     form
    0.84
    form
    0.70
     term
    0.68
     context
    0.66
     NSCoder
    0.62
    case
    0.61
     anyway
    0.59
    forms
    0.59
    Искәрмәләр
    0.59
    FORMS
    0.58
    Activations Density 2.961%

    No Known Activations