© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11394
    Prev
    Next
    INDEX
    Explanations

    technical writing about lasers and photons

    oai_token-act-pair · gemini-2.0-flash

    lasers and physics

    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
    脚注の使い方
    -0.95
    клопе
    -0.93
     kaynağından
    -0.77
    GEBURTSDATUM
    -0.77
    awtextra
    -0.76
     disponibilités
    -0.74
     فريبيس
    -0.74
    Билгалдахарш
    -0.72
    AddHtmlAttribute
    -0.71
    Vidite
    -0.69
    POSITIVE LOGITS
     p
    0.47
    ={({
    0.47
    cusión
    0.40
    FailureListener
    0.40
    CHAFT
    0.40
    UnknownFields
    0.40
    luft
    0.40
    denn
    0.40
    ushchev
    0.39
    Champaign
    0.39
    Activations Density 3.865%

    No Known Activations