© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9256
    Prev
    Next
    INDEX
    Explanations

    sentences containing the phrase "want to"

    oai_token-act-pair · gemini-2.0-flash

    wanting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Referanser
    -0.53
    linker
    -0.51
    
    -0.50
    igshid
    -0.50
    anyl
    -0.49
    Queryable
    -0.47
    InstanceState
    -0.46
     Lagu
    -0.46
     ISNI
    -0.46
     delas
    -0.45
    POSITIVE LOGITS
     OFDb
    0.80
     ProtoMessage
    0.74
     للاسماء
    0.66
     विश्वसनीयता
    0.65
     CreateTagHelper
    0.62
     kaarangay
    0.62
    ]--;
    0.60
     CURLOPT
    0.59
    ỡng
    0.58
     autorytatywna
    0.56
    Activations Density 4.065%

    No Known Activations