© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15305
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "do" or "does" in various tenses and forms, often in legal or semi-technical contexts.

    oai_token-act-pair · gemini-2.0-flash

    does/did

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     does
    -0.81
    tagHelperRunner
    -0.75
     did
    -0.74
    does
    -0.68
    Does
    -0.65
     do
    -0.62
     Does
    -0.61
    did
    -0.61
    DOES
    -0.55
     DID
    -0.53
    POSITIVE LOGITS
     tartalomajánló
    0.65
     상세
    0.63
     springfox
    0.62
    ondissement
    0.61
    assertj
    0.59
     unknownFields
    0.57
     Мексичка
    0.57
    responseType
    0.56
    KommentareTeilen
    0.55
    Xna
    0.54
    Activations Density 14.048%

    No Known Activations