© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4912
    Prev
    Next
    INDEX
    Explanations

    mentions of seas and beaches

    oai_token-act-pair · gemini-2.0-flash

    sea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     moeite
    -0.68
     expéri
    -0.65
    llave
    -0.65
     belangrij
    -0.60
     oubli
    -0.56
     marins
    -0.56
     gevallen
    -0.56
     república
    -0.56
     Frick
    -0.55
     Révolution
    -0.53
    POSITIVE LOGITS
     صوتيه
    0.98
     utafitiHapana
    0.91
     CreateTagHelper
    0.90
     الحره
    0.77
    Jeografia
    0.76
    AndEndTag
    0.73
    
    0.72
    GEBURTSDATUM
    0.71
    Viited
    0.71
     كومونز
    0.71
    Activations Density 1.226%

    No Known Activations