© 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. 3503
    Prev
    Next
    INDEX
    Explanations

    phrases about movement and things coming to mind.

    oai_token-act-pair · gemini-2.0-flash

    unusual proper nouns or foreign terms

    np_token-act-pair-logits · gpt-4o-mini

    Events

    np_max-act-logits · gemini-2.0-flash
    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
     come
    -1.29
     coming
    -1.25
     comes
    -1.23
     arrive
    -1.16
     arrives
    -1.15
     Coming
    -1.05
     came
    -1.05
     arriving
    -1.05
     Comes
    -1.04
    Coming
    -1.03
    POSITIVE LOGITS
    Manbalar
    0.66
    Tikang
    0.64
     propOrder
    0.63
    setVerticalGroup
    0.57
    ThroughAttribute
    0.57
    hésite
    0.56
    ніципалі
    0.56
    তথ্যসূত্র
    0.55
    Попис
    0.53
    ̍t
    0.52
    Activations Density 1.773%

    No Known Activations