© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3084
    Prev
    Next
    INDEX
    Explanations

    the preposition "on" followed by nouns or noun phrases about time and place, and verbs referring to actions or states.

    oai_token-act-pair · gemini-2.0-flash

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -1.27
    <bos>
    -1.20
    On
    -0.73
     On
    -0.69
     على
    -0.57
     sulla
    -0.55
     ON
    -0.50
     thereon
    -0.50
     vpon
    -0.49
     روی
    -0.48
    POSITIVE LOGITS
     تانيه
    0.82
    ChildScrollView
    0.69
    Datuak
    0.64
     BrowserModule
    0.60
    FirstResponder
    0.60
    ollectionView
    0.59
     EconPapers
    0.59
     Organizer
    0.59
    ----</
    0.59
    orney
    0.58
    Activations Density 5.472%

    No Known Activations