© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13174
    Prev
    Next
    INDEX
    Explanations

    java code and JSON data

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ());
    -1.53
    ())
    -1.50
    ());
    -1.44
    ()))
    -1.41
    ()));
    -1.41
    ()).
    -1.38
    ();
    -1.34
    ();
    -1.34
    ())
    -1.33
    ().
    -1.30
    POSITIVE LOGITS
     Prid
    0.57
     humaine
    0.53
    argout
    0.52
     germ
    0.52
    ็จ
    0.51
     stained
    0.50
     stain
    0.49
     Stain
    0.48
    neat
    0.48
     neat
    0.47
    Activations Density 5.521%

    No Known Activations