© 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. 10754
    Prev
    Next
    INDEX
    Explanations

    the prefix "unre" which probably means unreacted

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical

    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
    abestanden
    -0.64
     defaultstate
    -0.56
     EconPapers
    -0.54
    ChildScrollView
    -0.49
    Дереккөздер
    -0.48
    KURZBESCHREIBUNG
    -0.47
    ביוגרפיה
    -0.46
    最快更新
    -0.46
    __(/*!
    -0.45
    kuuta
    -0.45
    POSITIVE LOGITS
    ssing
    0.59
    dient
    0.59
    st
    0.58
    出版年
    0.57
    ss
    0.57
    ssan
    0.57
    efes
    0.56
     Вікі
    0.54
    cq
    0.53
    ciated
    0.52
    Activations Density 2.134%

    No Known Activations