© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7689
    Prev
    Next
    INDEX
    Explanations

    code snippets where encoding or decoding or used

    oai_token-act-pair · gemini-2.0-flash

    encode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     a
    -0.86
     the
    -0.82
     
    -0.77
     in
    -0.76
     an
    -0.70
     '
    -0.70
     "
    -0.69
     I
    -0.69
     so
    -0.67
     He
    -0.66
    POSITIVE LOGITS
     purpoſe
    1.71
     ſche
    1.67
     houſe
    1.65
     ſtate
    1.65
     pleaſure
    1.60
     Monfieur
    1.60
     myſelf
    1.59
     preſent
    1.59
     ainfi
    1.58
     ſch
    1.55
    Activations Density 0.598%

    No Known Activations