© 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. 5089
    Prev
    Next
    INDEX
    Explanations

    phrases with auxiliary verbs expressing possibility, conditionality, or speculation

    oai_token-act-pair · gemini-2.0-flash

    Negative past events

    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
     occur
    -2.20
     occurs
    -2.08
     happen
    -2.03
     happens
    -1.99
     happening
    -1.83
     occurring
    -1.83
    happens
    -1.83
    occurs
    -1.80
     occurred
    -1.78
     Happens
    -1.67
    POSITIVE LOGITS
    semantics
    0.56
     ${({
    0.46
     throats
    0.46
    WEAK
    0.46
    uasion
    0.45
     rendel
    0.45
    mobileqq
    0.44
     Triassic
    0.44
     Pliocene
    0.44
    sera
    0.44
    Activations Density 2.712%

    No Known Activations