© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8403
    Prev
    Next
    INDEX
    Explanations

    mentions of collaborative activities and collective success

    oai_token-act-pair · gemini-2.0-flash

    together

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IVEREF
    -0.52
     tyle
    -0.48
     насељу
    -0.47
    idać
    -0.45
     aload
    -0.45
    ینک
    -0.42
    miyorum
    -0.40
     링크
    -0.40
    دانشنامهٔ
    -0.40
     Minden
    -0.40
    POSITIVE LOGITS
     together
    2.77
    together
    2.45
     Together
    2.39
    Together
    2.33
     TOGETHER
    2.11
     juntos
    2.06
     jointly
    1.62
     insieme
    1.60
     bersama
    1.59
     zusammen
    1.59
    Activations Density 0.927%

    No Known Activations