© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6768
    Prev
    Next
    INDEX
    Explanations

    initialisms paired with fragments of scientific words, especially related to biology, chemistry, or medicine.

    oai_token-act-pair · gemini-2.0-flash

    ec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ec
    -1.14
    EC
    -1.02
    vec
    -0.76
     EC
    -0.75
    ECs
    -0.72
    ecu
    -0.66
     ec
    -0.65
    ecs
    -0.64
    Ec
    -0.64
    AndEndTag
    -0.62
    POSITIVE LOGITS
     GenerationType
    0.69
    LITERAL
    0.65
    qrstuvwxyz
    0.59
    sistors
    0.59
    σθαι
    0.58
    EDEFAULT
    0.56
     ComVisible
    0.55
    พาะ
    0.54
    >{@
    0.54
    tanleria
    0.54
    Activations Density 7.541%

    No Known Activations