© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13768
    Prev
    Next
    INDEX
    Explanations

    words related to software programs and/or accredited academic departments

    oai_token-act-pair · gemini-2.0-flash

    program

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AddTagHelper
    -0.88
     مشين
    -0.86
    IVEREF
    -0.83
    AndEndTag
    -0.82
    numerusform
    -0.79
    astify
    -0.76
    setVerticalGroup
    -0.75
    StructEnd
    -0.75
    basicConfig
    -0.75
    AxisAlignment
    -0.73
    POSITIVE LOGITS
    medes
    0.47
    med
    0.41
    cesis
    0.40
    odan
    0.39
    mes
    0.39
    yente
    0.38
    τέ
    0.38
    ming
    0.37
    MING
    0.37
     ус
    0.36
    Activations Density 3.853%

    No Known Activations