© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11060
    Prev
    Next
    INDEX
    Explanations

    words related to motion or movement, especially coming or going.

    oai_token-act-pair · gemini-2.0-flash

    motion and/or negative emotion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    richTextPanel
    -0.64
    তথ্যসূত্র
    -0.63
    ernet
    -0.62
    InjectAttribute
    -0.61
    tagext
    -0.57
     casó
    -0.55
     <<<<<<<<<<<<<<
    -0.52
    Externé
    -0.51
    منابع
    -0.50
    FieldBuilder
    -0.49
    POSITIVE LOGITS
     hurt
    0.65
     care
    0.63
     flying
    0.62
    Care
    0.56
     crashing
    0.51
    torn
    0.51
     Care
    0.50
    asanjo
    0.50
     sailing
    0.50
     tearing
    0.50
    Activations Density 3.782%

    No Known Activations