© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7091
    Prev
    Next
    INDEX
    Explanations

    words or phrases commonly found in bibliographies, reviews, or other descriptions of creative works

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    IndentedString
    -0.56
    _=
    -0.47
    достатки
    -0.46
    Rohy
    -0.46
     Duisburg
    -0.45
    __);
    -0.44
     formaggio
    -0.44
    RunAsync
    -0.44
    yatı
    -0.43
     UAB
    -0.43
    POSITIVE LOGITS
     فريبيس
    0.66
     المعيارى
    0.59
    celotti
    0.59
    جستارهای
    0.58
    iddhar
    0.56
    jsonwebtoken
    0.55
    interopRequire
    0.55
    ntable
    0.54
    Gön
    0.54
    Personensuche
    0.53
    Activations Density 5.715%

    No Known Activations