© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10089
    Prev
    Next
    INDEX
    Explanations

    plural nouns

    oai_token-act-pair · gemini-2.0-flash

    steps

    np_max-act-logits · gemini-2.0-flash

    technical terms and names in a specific format

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ParallelGroup
    -0.55
    ghts
    -0.49
    ніципа
    -0.48
    ites
    -0.43
     teljesen
    -0.43
    head
    -0.42
    Activités
    -0.41
    ITES
    -0.40
    handle
    -0.39
    OWER
    -0.39
    POSITIVE LOGITS
     MainAxisSize
    0.65
     typelib
    0.64
    StoreMessageInfo
    0.63
    Gweler
    0.60
     TextAppearance
    0.60
    exitRule
    0.59
     Bluestacks
    0.59
    estream
    0.58
     RouterModule
    0.57
    =$?
    0.56
    Activations Density 0.827%

    No Known Activations