© 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. 1428
    Prev
    Next
    INDEX
    Explanations

    uses of the auxiliary verbs "to have" and "to do"

    oai_token-act-pair · gemini-2.0-flash

    forms of "have"

    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
     intptr
    -0.80
    
    -0.73
     typelib
    -0.63
    tvguidetime
    -0.62
    GraphicsUnit
    -0.58
    NameInMap
    -0.56
    χρι
    -0.56
    __":
    -0.55
     Roskov
    -0.55
     MainAxisSize
    -0.54
    POSITIVE LOGITS
     OMITBAD
    0.58
     holding
    0.56
     swept
    0.54
     dancing
    0.54
     strolling
    0.54
     harassed
    0.54
    richTextPanel
    0.54
     attending
    0.53
     executed
    0.53
     Addressing
    0.53
    Activations Density 6.285%

    No Known Activations