© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12431
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     continúas
    -0.82
    windowFixed
    -0.69
    PreferredItem
    -0.63
     considérons
    -0.62
    AnchorStyles
    -0.60
     initComponents
    -0.59
     löyty
    -0.58
    brigens
    -0.56
    unzione
    -0.56
    RenderAtEndOf
    -0.56
    POSITIVE LOGITS
     the
    0.68
     that
    0.63
     a
    0.57
     front
    0.48
    subpackage
    0.47
    yg
    0.47
    ativity
    0.46
    THM
    0.46
    ècle
    0.46
     an
    0.45
    Activations Density 1.920%

    No Known Activations