© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8201
    Prev
    Next
    INDEX
    Explanations

    the word 'part' or 'parts' which refers to components in a system

    oai_token-act-pair · gemini-2.0-flash

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     part
    -2.44
    part
    -1.52
     parte
    -1.37
     часть
    -1.30
    Part
    -1.18
     Part
    -1.13
     частью
    -1.13
     Teil
    -1.12
     onderdeel
    -1.04
     część
    -1.02
    POSITIVE LOGITS
     renseignements
    0.69
     artigian
    0.58
    BufferException
    0.55
     masculino
    0.54
    enti
    0.54
     artig
    0.54
     fatos
    0.51
     evolução
    0.51
     demais
    0.50
     förm
    0.50
    Activations Density 1.015%

    No Known Activations