Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 10128
    Prev
    Next
    INDEX
    Explanations

    the word "such" or parts of the word, as well as miscellaneous other short words/syllables

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Verder
    -0.58
     vado
    -0.51
    Cursors
    -0.50
    IndentedString
    -0.50
     Herzegovina
    -0.48
    gnügen
    -0.48
    BeginContext
    -0.47
    Gesamt
    -0.47
    HttpPut
    -0.45
     Cera
    -0.45
    POSITIVE LOGITS
     such
    1.94
    Such
    1.77
    such
    1.77
     Such
    1.70
     SUCH
    1.51
     solche
    1.32
     solchen
    1.24
     таких
    1.16
     такой
    1.15
     такие
    1.15
    Activations Density 0.489%

    No Known Activations