© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10305
    Prev
    Next
    INDEX
    Explanations

    strings containing what look like abbreviations followed by a possessive apostrophe

    oai_token-act-pair · gemini-2.0-flash

    technical texts

    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
    ıyordu
    -0.99
    ılıyor
    -0.96
    acağı
    -0.91
    ırken
    -0.91
    ıyors
    -0.90
    ıldığı
    -0.84
    ıyoruz
    -0.82
    ılmıştır
    -0.80
    ılacak
    -0.80
    acaktır
    -0.80
    POSITIVE LOGITS
    in
    0.52
    ini
    0.52
     חיצוניים
    0.50
    inin
    0.50
    liato
    0.48
    isi
    0.48
     الحره
    0.47
     da
    0.47
     handker
    0.45
    inawa
    0.45
    Activations Density 2.562%

    No Known Activations