© 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. 12533
    Prev
    Next
    INDEX
    Explanations

    non-English characters and code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code and data stuff

    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
    verständlich
    -0.48
     PFA
    -0.46
     Cfr
    -0.46
    ;";
    -0.45
    .")
    -0.45
    ToRefresh
    -0.45
    PRNewswire
    -0.44
     Allein
    -0.43
     PWR
    -0.42
     Dox
    -0.42
    POSITIVE LOGITS
    Datuak
    0.90
     nahilalakip
    0.75
     élas
    0.68
     présidenti
    0.66
    matchCondition
    0.64
     bonté
    0.63
     endblock
    0.62
    wydd
    0.60
     rempliss
    0.60
    Enllaces
    0.60
    Activations Density 0.592%

    No Known Activations