© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10998
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing choice and decision-making plus some related tech terms

    oai_token-act-pair · gemini-2.0-flash

    pick

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     بيها
    -0.63
     choice
    -0.63
    richTextPanel
    -0.62
    choice
    -0.60
    Choice
    -0.60
    Rhestr
    -0.57
    TestingModule
    -0.54
    :✨
    -0.54
     choices
    -0.53
    stddef
    -0.52
    POSITIVE LOGITS
     pick
    3.38
    pick
    3.13
    Pick
    3.06
     Pick
    3.06
     picked
    3.00
     picking
    2.88
     PICK
    2.86
     picks
    2.77
     Picking
    2.61
    PICK
    2.53
    Activations Density 9.995%

    No Known Activations