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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9365
    Prev
    Next
    INDEX
    Explanations

    scientific research articles

    oai_token-act-pair · gemini-2.0-flash

    Cancer research and statistics

    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
     slightly
    -0.75
     completamente
    -0.73
    completely
    -0.71
     completely
    -0.71
     totalmente
    -0.66
    Slightly
    -0.65
    slightly
    -0.65
     Completely
    -0.64
     Slightly
    -0.63
    Completely
    -0.63
    POSITIVE LOGITS
     sign
    0.73
    abestanden
    0.72
     дописавши
    0.68
    Sign
    0.60
     disappoint
    0.57
    DllImport
    0.56
    NameInMap
    0.55
     Sign
    0.54
     signe
    0.54
     disgust
    0.54
    Activations Density 9.098%

    No Known Activations