© 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. 6830
    Prev
    Next
    INDEX
    Explanations

    parts of Java code related to object instantiation, conditions, and certain keywords

    oai_token-act-pair · gemini-2.0-flash

    special characters and formatting elements

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

    Code snippets

    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
     Monfieur
    -1.10
     betweenstory
    -1.09
     itſelf
    -1.05
     myſelf
    -1.04
     beginnetje
    -1.03
     <=",
    -1.03
     متعلقه
    -1.00
    AndEndTag
    -1.00
    ConstraintMaker
    -0.99
     surla
    -0.97
    POSITIVE LOGITS
    '
    0.51
     
    0.50
    0.48
    <eos>
    0.48
    asList
    0.45
    ’
    0.45
    ImGui
    0.45
     y
    0.44
     v
    0.44
    <bos>
    0.44
    Activations Density 7.008%
    No Known Activations