© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5598
    Prev
    Next
    INDEX
    Explanations

    text related to quantum physics experiments

    oai_token-act-pair · gemini-2.0-flash

    terms related to particles and molecules

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

    atoms and molecules

    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
     BoxDecoration
    -0.59
     disambiguazione
    -0.52
     })
    -0.51
    homonymie
    -0.50
    انجليز
    -0.49
    verwijspagina
    -0.49
    Portály
    -0.49
    Notae
    -0.48
    Itoa
    -0.47
    انيف
    -0.47
    POSITIVE LOGITS
     molecules
    1.01
     particles
    0.89
     molecule
    0.85
     atoms
    0.84
     Molecules
    0.79
     cells
    0.77
    atoms
    0.75
    molecules
    0.75
     molé
    0.74
     particules
    0.73
    Activations Density 6.313%

    No Known Activations