© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10009
    Prev
    Next
    INDEX
    Explanations

    noun phrases that describe scientific fields or technologies, especially when describing work that has been done or potential for current/future work.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "gain"

    np_token-act-pair-logits · gpt-4o-mini

    gain

    np_max-act-logits · gemini-2.0-flash
    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
    TypedDataSet
    -0.94
    StructEnd
    -0.70
    protoc
    -0.59
    ulipas
    -0.58
    Jereo
    -0.57
    zkiem
    -0.57
     useSelector
    -0.56
    icksburg
    -0.55
    rąg
    -0.55
    ]")]
    -0.55
    POSITIVE LOGITS
     gained
    0.99
     gain
    0.95
     gaining
    0.91
    gain
    0.91
     Gain
    0.82
     gains
    0.82
    Gain
    0.81
     GAIN
    0.66
    gains
    0.64
    GAIN
    0.62
    Activations Density 3.011%

    No Known Activations