© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4001
    Prev
    Next
    INDEX
    Explanations

    java code

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ")(
    -0.54
     chọn
    -0.52
    เลือก
    -0.50
    kloped
    -0.50
    arbox
    -0.49
    )$\\
    -0.49
    ilih
    -0.46
     AssemblyProduct
    -0.46
     pilihan
    -0.45
     Hickey
    -0.45
    POSITIVE LOGITS
     <=",
    0.73
    thâu
    0.68
    __":
    0.66
     ExecuteAsync
    0.65
     Allociné
    0.64
     Roskov
    0.63
    __':
    0.63
    WebElementEntity
    0.60
    mybatisplus
    0.59
     يتيمه
    0.56
    Activations Density 2.952%

    No Known Activations