© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5423
    Prev
    Next
    INDEX
    Explanations

    the auxiliary verb "has" and some other forms of "have"

    oai_token-act-pair · gemini-2.0-flash

    has

    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
    Has
    -0.56
     Has
    -0.55
     has
    -0.53
    WithMany
    -0.51
     viewDidLoad
    -0.51
    djangoproject
    -0.50
     takes
    -0.48
     dernier
    -0.47
    Was
    -0.47
     Took
    -0.47
    POSITIVE LOGITS
    GraphicsUnit
    0.60
    anskje
    0.59
    ynchronously
    0.59
    Abitanti
    0.58
    Identyfik
    0.58
    IndentedString
    0.56
     numerus
    0.56
    تفصیلات
    0.55
    تقاوى
    0.55
    quelize
    0.55
    Activations Density 0.522%

    No Known Activations