© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    XML tags.

    oai_token-act-pair · gemini-2.0-flash

    Software/data configurations

    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
     food
    -1.12
     medical
    -1.05
     music
    -1.05
     wine
    -0.99
     health
    -0.94
     coffee
    -0.94
     wildlife
    -0.93
     sports
    -0.93
     electricity
    -0.91
    music
    -0.90
    POSITIVE LOGITS
     paso
    0.53
    GraphicsUnit
    0.52
    RegressionTest
    0.51
     subpart
    0.50
    SuppressMessage
    0.50
     passo
    0.50
     rank
    0.49
     pass
    0.49
    WebControls
    0.49
     holder
    0.49
    Activations Density 10.932%

    No Known Activations