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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6389
    Prev
    Next
    INDEX
    Explanations

    text related to components of hidden markov models and bayesian networks along with the math/cs theory concepts for them

    oai_token-act-pair · gemini-2.0-flash

    data-related terms

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

    Academic research papers

    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
     AssemblyCulture
    -0.69
    存于互联网档案馆
    -0.67
     âgées
    -0.66
     démission
    -0.63
    aarrggbb
    -0.55
     neutre
    -0.54
     cooperativa
    -0.53
    enderror
    -0.53
     chrétiens
    -0.53
     soldati
    -0.52
    POSITIVE LOGITS
     pair
    0.56
     observed
    0.56
    ximity
    0.54
    queryInterface
    0.53
    Taille
    0.52
     feature
    0.51
     output
    0.51
    specialchars
    0.50
     features
    0.49
     createSprite
    0.49
    Activations Density 11.640%

    No Known Activations