© 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. 6351
    Prev
    Next
    INDEX
    Explanations

    words related to skills, interests, or diseases, and also the Portuguese word "atividades" (activities)

    oai_token-act-pair · gemini-2.0-flash

    Multi-lingual technical writing

    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
    Elles
    -1.17
     elles
    -1.06
     Elles
    -1.02
     שונים
    -0.90
     ellas
    -0.87
     חיצוניים
    -0.85
     celles
    -0.84
     אחרים
    -0.74
     suivants
    -0.73
     franceses
    -0.73
    POSITIVE LOGITS
    BeginContext
    0.56
     ejus
    0.55
     Signalez
    0.49
    lador
    0.48
    Mediabestanden
    0.47
     autorytatywna
    0.45
     tasca
    0.45
    ArgsConstructor
    0.45
    centralwidget
    0.45
    fillColor
    0.44
    Activations Density 1.756%

    No Known Activations