© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10114
    Prev
    Next
    INDEX
    Explanations

    words related to knowledge and ability to do things, often in the context of multiple languages or programming

    oai_token-act-pair · gemini-2.0-flash

    Romance languages verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    новниш
    -0.64
    ahashi
    -0.63
     Tenden
    -0.59
    ạnh
    -0.56
     gere
    -0.56
     mengel
    -0.54
    رشف
    -0.54
    vig
    -0.54
    teness
    -0.53
    datagrid
    -0.52
    POSITIVE LOGITS
     learned
    1.13
     learnt
    1.11
     learn
    1.10
     learns
    1.05
     learning
    1.05
     know
    1.05
    know
    1.03
    learned
    1.03
    Know
    1.03
    Learn
    1.02
    Activations Density 0.697%

    No Known Activations