© 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. 15579
    Prev
    Next
    INDEX
    Explanations

    code and configuration settings

    oai_token-act-pair · gemini-2.0-flash

    Code and configuration

    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
     enfans
    -0.38
     avoient
    -0.33
     définiti
    -0.32
     générations
    -0.29
     vägen
    -0.29
     étoient
    -0.28
     spéciaux
    -0.28
     élas
    -0.27
     rapides
    -0.27
     clô
    -0.27
    POSITIVE LOGITS
    vábbi
    0.64
    EDEFAULT
    0.59
    ETRY
    0.58
    utnik
    0.58
    ykjav
    0.56
     Permalink
    0.56
    ÇO
    0.55
    SCRIBE
    0.54
     CURLOPT
    0.54
     fallout
    0.54
    Activations Density 10.925%

    No Known Activations