© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1426
    Prev
    Next
    INDEX
    Explanations

    dates and times in past events

    oai_token-act-pair · gemini-2.0-flash

    beginnings, requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    InSection
    -0.58
    nologue
    -0.52
     gyhoeddwyd
    -0.50
     semej
    -0.50
    
    -0.50
    endpush
    -0.49
     próximos
    -0.49
    PageContext
    -0.48
    guous
    -0.47
    Parcelize
    -0.47
    POSITIVE LOGITS
     ſeveral
    0.59
     Aristi
    0.59
     pleaſure
    0.58
     fevere
    0.56
    ſelves
    0.53
     purpoſe
    0.53
     houſe
    0.53
    ptos
    0.51
     ſmall
    0.51
     Réalisation
    0.51
    Activations Density 1.083%

    No Known Activations