© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10239
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns describing something restricted or weaker than expected

    oai_token-act-pair · gemini-2.0-flash

    degree, amount, or quantity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     fubject
    -0.65
     ſta
    -0.64
     raiſ
    -0.64
     ſub
    -0.60
    setopt
    -0.60
     leſs
    -0.59
     themſelves
    -0.58
     myſelf
    -0.58
     poffe
    -0.58
    WithMany
    -0.57
    POSITIVE LOGITS
     تضيفلها
    0.69
    enoord
    0.52
    ripple
    0.50
     rozum
    0.50
    lccn
    0.49
    orld
    0.49
    favorited
    0.48
    ArrowToggle
    0.48
    提
    0.47
    коменду
    0.46
    Activations Density 0.616%

    No Known Activations