© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8755
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to academic studies and research

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueGeneration
    -0.61
    ])).
    -0.48
     femininas
    -0.47
    Framework
    -0.45
    multipart
    -0.44
    ).
    -0.44
    ズム
    -0.43
    GEBURTSDATUM
    -0.43
     AppModule
    -0.43
     çağ
    -0.43
    POSITIVE LOGITS
    BeginContext
    0.71
    Chham
    0.68
    newArrayList
    0.65
    Життєпис
    0.60
    NOPQRST
    0.59
    mybatisplus
    0.59
    ContentAlignment
    0.59
     BoxDecoration
    0.58
    transQ
    0.57
    RefNanny
    0.57
    Activations Density 0.659%

    No Known Activations