© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4474
    Prev
    Next
    INDEX
    Explanations

    the word "in" when followed by attribution to something written or said

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Espèce
    -0.58
     GenerationType
    -0.56
    setVerticalGroup
    -0.53
    ftagPool
    -0.53
    ūs
    -0.53
    featureID
    -0.53
    AddTagHelper
    -0.52
    MigrationBuilder
    -0.50
    setopt
    -0.50
    TableBody
    -0.50
    POSITIVE LOGITS
     doInBackground
    0.48
     دیکھیے
    0.47
     nettsted
    0.47
    XmlAccessType
    0.47
    Kanpo
    0.47
     Causeway
    0.46
    glement
    0.46
     censiti
    0.45
     PackageManager
    0.45
    wpdb
    0.45
    Activations Density 0.907%

    No Known Activations