© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9685
    Prev
    Next
    INDEX
    Explanations

    phrases about investing time, effort, or resources into something, or alternatively, bloody and violent events

    oai_token-act-pair · gemini-2.0-flash

    investment and effort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Favor
    -0.61
     OnTriggerEnter
    -0.54
    anskje
    -0.54
    messageInfo
    -0.51
    gonic
    -0.50
    hasMoreElements
    -0.49
    Favor
    -0.49
     Zahn
    -0.49
     Graphite
    -0.48
    immel
    -0.48
    POSITIVE LOGITS
     للاسماء
    0.76
     estekak
    0.62
    NewUrlParser
    0.62
    KommentareTeilen
    0.60
    Erstellt
    0.55
    ciatore
    0.54
    Investing
    0.52
     invokingState
    0.52
     صوتيه
    0.52
     прилага
    0.49
    Activations Density 0.245%

    No Known Activations