© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5159
    Prev
    Next
    INDEX
    Explanations

    filler words that appear in official publications

    oai_token-act-pair · gemini-2.0-flash

    business, management

    np_max-act-logits · 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
    šanu
    -0.41
    be
    -0.40
    I
    -0.39
     revés
    -0.38
    šanai
    -0.38
    h
    -0.37
    It
    -0.37
    Be
    -0.36
    vi
    -0.35
     nationales
    -0.35
    POSITIVE LOGITS
     الحره
    0.94
    BeginContext
    0.91
    WithIOException
    0.86
     صوتيه
    0.78
     Normdatei
    0.75
     making
    0.74
    ThroughAttribute
    0.73
     removing
    0.73
    addCriterion
    0.73
     substituting
    0.72
    Activations Density 4.275%

    No Known Activations