© 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. 5793
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe how a value changes, particularly increases and decreases, often in the context of scientific or mathematical relationships

    oai_token-act-pair · gemini-2.0-flash

    increases/decreases

    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
     незавершена
    -0.67
    __":
    -0.66
    دانشنامهٔ
    -0.65
     CURIAM
    -0.62
    __":
    -0.58
    __':
    -0.57
    Geplaatst
    -0.54
     EconPapers
    -0.54
    onOptions
    -0.53
     дописавши
    -0.53
    POSITIVE LOGITS
    ciera
    0.52
    raszamy
    0.47
    mona
    0.46
     inconnu
    0.46
    etra
    0.45
    ⓘ
    0.44
    siasi
    0.43
    aspectj
    0.43
     tố
    0.41
    elman
    0.41
    Activations Density 3.749%

    No Known Activations