© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9557
    Prev
    Next
    INDEX
    Explanations

    the verb "to do" or auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating actions or states

    np_token-act-pair-logits · gpt-4o-mini

    do/does

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     itſelf
    -0.76
     indisponible
    -0.75
     للاسماء
    -0.75
    awtextra
    -0.71
     contextLoads
    -0.71
    "]));
    -0.68
     ſmall
    -0.68
    enschappe
    -0.68
     iſt
    -0.68
     occaf
    -0.67
    POSITIVE LOGITS
     lead
    0.63
     imply
    0.60
     offer
    0.58
     not
    0.56
     become
    0.55
     constitute
    0.54
     resemble
    0.54
     remind
    0.52
     consist
    0.51
     contain
    0.51
    Activations Density 0.773%

    No Known Activations