© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12302
    Prev
    Next
    INDEX
    Explanations

    instances of the phrasal verb "call on".

    oai_token-act-pair · gemini-2.0-flash

    on/upon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     on
    -1.47
     On
    -0.77
     ON
    -0.72
    on
    -0.71
    On
    -0.66
     على
    -0.63
    บน
    -0.58
     на
    -0.58
    onUpdate
    -0.57
     πάνω
    -0.56
    POSITIVE LOGITS
     Meksiku
    1.05
    verwijspagina
    1.02
    awtextra
    0.99
    StoryboardSegue
    0.98
    <bos>
    0.97
    NameInMap
    0.97
    TagMode
    0.96
    AddTagHelper
    0.95
    UnknownFieldSet
    0.93
     AssemblyCompany
    0.92
    Activations Density 0.412%

    No Known Activations