© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8658
    Prev
    Next
    INDEX
    Explanations

    uses of "it", "that", "how", "will" and "can" in context

    oai_token-act-pair · gemini-2.0-flash

    words and concepts related to work and productivity

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SharedDtor
    -0.98
     للمعارف
    -0.87
     >=",
    -0.86
    èlement
    -0.82
     Efq
    -0.82
    脚注の使い方
    -0.77
    AutoresizingMask
    -0.74
    GOTREF
    -0.72
     <<<<<<<<<<<<<<
    -0.71
    Datuak
    -0.71
    POSITIVE LOGITS
    ètres
    0.44
    arbe
    0.42
    schedulers
    0.41
     influência
    0.41
    刊
    0.40
    ImageIO
    0.40
     works
    0.39
     work
    0.39
    werk
    0.39
     arbe
    0.39
    Activations Density 5.995%

    No Known Activations