© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5484
    Prev
    Next
    INDEX
    Explanations

    academic or technical writing discussing scientific results with focus on models and measurements

    oai_token-act-pair · gemini-2.0-flash

    exactness

    np_max-act-logits · 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
    Personensuche
    -0.66
    ThroughAttribute
    -0.57
    EndProject
    -0.55
     initComponents
    -0.53
    writeField
    -0.51
    izzano
    -0.50
    enumii
    -0.49
    makeText
    -0.49
     jadx
    -0.47
     Vikipedi
    -0.47
    POSITIVE LOGITS
     exactly
    2.55
     precisely
    2.50
    exactly
    2.33
     Exactly
    2.14
     EXACTLY
    2.09
    Exactly
    2.02
     exactement
    1.90
     exatamente
    1.85
     exact
    1.84
     exactamente
    1.77
    Activations Density 13.105%

    No Known Activations