© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13190
    Prev
    Next
    INDEX
    Explanations

    words related to forming a physical part of something

    oai_token-act-pair · gemini-2.0-flash

    portion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Portion
    -0.87
     portion
    -0.86
    portion
    -0.86
     Coefficient
    -0.86
     coefficient
    -0.85
     myſelf
    -0.83
     Efq
    -0.82
    Portion
    -0.80
     portions
    -0.79
     Portions
    -0.79
    POSITIVE LOGITS
    <bos>
    0.86
    tagHelper
    0.58
    '
    0.52
    RegressionTest
    0.49
    难得
    0.46
    richTextPanel
    0.46
    "
    0.44
    '/>
    0.43
     features
    0.43
     насељу
    0.42
    Activations Density 3.195%

    No Known Activations