© 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. 10105
    Prev
    Next
    INDEX
    Explanations

    words related to semiconductors, electronic devices, and physics.

    oai_token-act-pair · gemini-2.0-flash

    semiconductors and superconductors

    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
     disambiguazione
    -0.76
    expandindo
    -0.69
     >=",
    -0.62
     nakalista
    -0.60
    ThroughAttribute
    -0.60
     насељу
    -0.58
    DIPSETTING
    -0.57
    OpenHelper
    -0.56
    inaires
    -0.55
     ویکی‌پدی
    -0.54
    POSITIVE LOGITS
    ticolo
    0.52
    ็จ
    0.49
    beelding
    0.48
    tych
    0.48
    Viited
    0.46
     SDS
    0.46
    hauer
    0.46
    liato
    0.45
     InputDecoration
    0.45
     SLS
    0.45
    Activations Density 10.450%

    No Known Activations