© 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. 6405
    Prev
    Next
    INDEX
    Explanations

    words related to people getting chosen for teams or positions or otherwise being assigned tasks

    oai_token-act-pair · gemini-2.0-flash

    prepositions

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

    Hired/selected/assigned

    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
     дописавши
    -0.92
    SourceChecksum
    -0.87
     nahilalakip
    -0.87
    󠁴
    -0.85
    ंदीखरीदारी
    -0.82
     calendriers
    -0.82
    expandindo
    -0.81
    脚注の使い方
    -0.81
    astéroïdes
    -0.80
    ]--;
    -0.79
    POSITIVE LOGITS
     to
    0.94
     by
    0.57
     as
    0.56
     with
    0.47
     along
    0.47
     in
    0.45
     into
    0.43
     уда
    0.41
     for
    0.39
     through
    0.38
    Activations Density 10.703%

    No Known Activations