© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12390
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases related to things being in position

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Place
    -0.79
     place
    -0.79
    place
    -0.77
    хьтан
    -0.75
    Place
    -0.72
     noqa
    -0.72
    PLACE
    -0.68
     PLACE
    -0.65
    исленность
    -0.56
    webElementXpaths
    -0.55
    POSITIVE LOGITS
     in
    0.94
    in
    0.55
     In
    0.52
     IN
    0.52
    In
    0.50
    ใน
    0.50
     Maß
    0.49
     inline
    0.46
     CEC
    0.46
    món
    0.45
    Activations Density 3.147%

    No Known Activations