© 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. 3986
    Prev
    Next
    INDEX
    Explanations

    mentions of the Global Counter-Terrorism Forum and its co-presidency transfer

    oai_token-act-pair · gemini-2.0-flash

    meetings and political events

    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
     الدولى
    -0.75
     Anſ
    -0.71
     AssemblyProduct
    -0.70
    enschappelijke
    -0.66
     Monfieur
    -0.66
    原始内容存档于
    -0.66
    tvguidetime
    -0.65
    脚注の使い方
    -0.65
     Reſ
    -0.65
     Conſ
    -0.65
    POSITIVE LOGITS
    multer
    0.50
     semej
    0.50
     emb
    0.49
    ете
    0.47
     devriez
    0.47
     recevrez
    0.45
    NavigationBar
    0.45
    irical
    0.44
    аз
    0.42
    veren
    0.42
    Activations Density 8.754%

    No Known Activations