© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4889
    Prev
    Next
    INDEX
    Explanations

    job titles in business and medicine

    oai_token-act-pair · gemini-2.0-flash

    words related to executive titles and roles

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

    job titles

    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
    #
    -0.52
    ⓧ
    -0.49
    はじめに
    -0.49
    /]
    -0.48
    TagHelper
    -0.47
    stdc
    -0.47
    名的
    -0.46
    ربای
    -0.45
    SuspendLayout
    -0.45
    ()]);
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.79
    InjectAttribute
    0.58
    eners
    0.56
     scorso
    0.56
     ब्रेकडाउन
    0.56
    enfone
    0.55
     оригіналу
    0.55
     whereof
    0.54
     appointing
    0.54
     of
    0.54
    Activations Density 3.948%

    No Known Activations