© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 955
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming code

    oai_token-act-pair · gemini-2.0-flash

    common nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    GraphicsUnit
    -0.61
    ghold
    -0.50
     subpart
    -0.49
    diera
    -0.49
     flank
    -0.48
    numerusform
    -0.48
     يتيمه
    -0.48
    zień
    -0.48
     subs
    -0.47
     rank
    -0.47
    POSITIVE LOGITS
     food
    1.06
     medical
    1.02
     music
    1.01
     wine
    0.94
     health
    0.90
     coffee
    0.87
     wildlife
    0.87
     electricity
    0.86
     energy
    0.85
     sports
    0.85
    Activations Density 4.480%

    No Known Activations