© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9665
    Prev
    Next
    INDEX
    Explanations

    uses of the word "you" followed by helping verbs

    oai_token-act-pair · gemini-2.0-flash

    want, wanting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ظر
    -0.50
    ucin
    -0.45
    eye
    -0.44
    Eye
    -0.43
     B
    -0.41
     Co
    -0.41
     M
    -0.40
     to
    -0.39
    NAMESPACE
    -0.39
    ılar
    -0.38
    POSITIVE LOGITS
     want
    1.54
    want
    1.30
     wants
    1.27
     wanna
    1.23
     wanting
    1.15
     Want
    1.14
     WANT
    1.09
    ConstraintMaker
    1.07
    Want
    1.07
    wants
    1.04
    Activations Density 0.792%

    No Known Activations