© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1894
    Prev
    Next
    INDEX
    Explanations

    words associated with charitable giving and community service

    oai_token-act-pair · gemini-2.0-flash

    community and aid-related terms

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

    charitable activities

    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
    horabuena
    -0.56
    principalTable
    -0.54
    rrggbb
    -0.53
     Gallimard
    -0.52
    setAge
    -0.52
     japonaise
    -0.52
     législ
    -0.52
     commerciales
    -0.51
    steering
    -0.50
    UnitTesting
    -0.50
    POSITIVE LOGITS
     families
    0.70
    crollView
    0.61
     Roskov
    0.58
    MemoryWarning
    0.57
    RenderAtEndOf
    0.57
    ProgressHUD
    0.56
    ագրություններ
    0.55
     residents
    0.55
    oa̍t
    0.55
     seniors
    0.54
    Activations Density 4.622%

    No Known Activations