© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3352
    Prev
    Next
    INDEX
    Explanations

    sports and political figures and/or acronyms, or technical terms such as in imaging

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -
    -0.77
     synap
    -0.76
     starlight
    -0.72
     virginity
    -0.70
     logarith
    -0.69
     degeneracy
    -0.69
     hemispheres
    -0.67
     sovereigns
    -0.67
     Cæsar
    -0.67
     divinity
    -0.67
    POSITIVE LOGITS
    %");
    0.88
     enfans
    0.84
     feroit
    0.83
    lijck
    0.81
    ſam
    0.81
     vérit
    0.80
     pitié
    0.80
     rayures
    0.79
     hâte
    0.79
     élas
    0.79
    Activations Density 11.405%

    No Known Activations