© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3884
    Prev
    Next
    INDEX
    Explanations

    words that end in a consonant followed by two lowercase letters

    oai_token-act-pair · gemini-2.0-flash

    tus

    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
    Negative Logits
    ReusableCell
    -0.81
    sizeCache
    -0.80
     Exacts
    -0.78
    帖最后由
    -0.74
     الدولى
    -0.71
    providedIn
    -0.70
    الدراسه
    -0.69
    LookAnd
    -0.67
    AddTagHelper
    -0.66
    AccessorTable
    -0.66
    POSITIVE LOGITS
     magasiner
    0.51
    Recall
    0.47
    tison
    0.46
    èbres
    0.44
    subscribed
    0.44
    idered
    0.44
    wohl
    0.43
    ︎
    0.43
     hẳn
    0.43
    ordinates
    0.42
    Activations Density 9.358%

    No Known Activations