© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4986
    Prev
    Next
    INDEX
    Explanations

    seemingly random technical or descriptive words

    oai_token-act-pair · gemini-2.0-flash

    past participles related to processing

    np_token-act-pair-logits · gpt-4o-mini

    past tense verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ēl
    -0.44
     étrangers
    -0.43
    dion
    -0.42
    Were
    -0.42
    жидан
    -0.40
     Were
    -0.40
    were
    -0.39
    severe
    -0.38
    ständige
    -0.38
    noble
    -0.38
    POSITIVE LOGITS
     extracted
    1.09
     rendered
    1.09
     edited
    1.02
     implemented
    1.01
     converted
    1.00
     exported
    1.00
     transported
    1.00
     planted
    0.99
     copied
    0.97
     brewed
    0.97
    Activations Density 4.456%

    No Known Activations