© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4137
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms consisting of prefixes, suffixes and root words which end in "m"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ement
    -0.58
    able
    -0.58
    ame
    -0.56
    ado
    -0.54
    ability
    -0.51
    aban
    -0.50
    aires
    -0.49
    aurus
    -0.49
    abilità
    -0.49
     kasarigan
    -0.48
    POSITIVE LOGITS
    AnchorTagHelper
    0.71
     AssemblyTitle
    0.57
     [*]
    0.57
    SupportActionBar
    0.55
    出版年
    0.54
    IBarButtonItem
    0.53
    :✨
    0.51
    Последние
    0.50
    baix
    0.49
     للمعارف
    0.49
    Activations Density 0.499%

    No Known Activations