© 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. 3991
    Prev
    Next
    INDEX
    Explanations

    descriptions of a topic

    oai_token-act-pair · gemini-2.0-flash

    concerned

    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
    principalColumn
    -0.59
    ureusement
    -0.57
    Przypisy
    -0.54
    Ẫ
    -0.54
    extAlignment
    -0.52
     ExecuteAsync
    -0.52
     navel
    -0.52
     withal
    -0.51
    imread
    -0.50
     initComponents
    -0.48
    POSITIVE LOGITS
     concerned
    1.88
    concerned
    1.66
     Concerned
    1.42
     concern
    1.34
     CONCERN
    1.30
     concerns
    1.22
     Concern
    1.15
    concern
    1.09
    concerns
    1.06
    Concer
    1.04
    Activations Density 0.493%

    No Known Activations