© 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. 11258
    Prev
    Next
    INDEX
    Explanations

    prepositions and related words in a document.

    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
    ValueStyle
    -0.99
    awtextra
    -0.66
    MemoryWarning
    -0.63
     AssemblyCulture
    -0.62
    AnchorStyles
    -0.60
    >(_
    -0.59
    ])){
    -0.59
     MenuView
    -0.58
    GeoNames
    -0.57
    mybatisplus
    -0.57
    POSITIVE LOGITS
    mtrl
    0.60
    phosa
    0.56
     interstate
    0.50
    lling
    0.48
     RSSSF
    0.48
     trouble
    0.47
    argento
    0.47
     labeled
    0.47
     houſe
    0.47
    arsch
    0.47
    Activations Density 2.268%

    No Known Activations