© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4283
    Prev
    Next
    INDEX
    Explanations

    the word "with" positioned near articles, adjectives, or prepositions

    oai_token-act-pair · gemini-2.0-flash

    With

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ReusableCell
    -0.78
    EndContext
    -0.78
    UrlResolution
    -0.67
    aarrggbb
    -0.64
     onOptions
    -0.63
     INTERESAR
    -0.63
    setVerticalGroup
    -0.63
    StoryboardSegue
    -0.62
     OMIT
    -0.61
    expandindo
    -0.61
    POSITIVE LOGITS
    ندر
    0.45
    మి
    0.41
     CommandType
    0.40
    adaptiveStyles
    0.40
     предела
    0.39
    нисти
    0.39
     karşılaş
    0.39
    beginTransaction
    0.39
    StringTo
    0.39
     self
    0.37
    Activations Density 2.365%

    No Known Activations