© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14556
    Prev
    Next
    INDEX
    Explanations

    words associated with the future tense

    oai_token-act-pair · gemini-2.0-flash

    Negation/Conditional statements

    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
     وتسجيلات
    -1.05
    Personensuche
    -0.87
    ArgsConstructor
    -0.84
     betweenstory
    -0.81
    forChild
    -0.79
    StructEnd
    -0.78
    PreferredItem
    -0.77
    tagHelperRunner
    -0.77
     gynhyrchwyd
    -0.77
    Viited
    -0.76
    POSITIVE LOGITS
     be
    0.60
     even
    0.55
     se
    0.47
     
    0.45
    ,
    0.43
     have
    0.42
    des
    0.42
     wish
    0.41
     e
    0.41
     st
    0.41
    Activations Density 1.414%

    No Known Activations