© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6785
    Prev
    Next
    INDEX
    Explanations

    content related to advertising and surveys

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
     la
    -0.72
     -
    -0.68
     [
    -0.66
     v
    -0.65
     den
    -0.63
     
    -0.62
     (
    -0.61
     M
    -0.61
     po
    -0.58
     T
    -0.58
    POSITIVE LOGITS
     pleaſure
    1.11
     itſelf
    1.11
     Monfieur
    1.09
     purpoſe
    1.08
     ſche
    1.03
     Jefus
    1.03
     Reſ
    1.03
     myſelf
    1.03
     ſtate
    1.02
     Diſ
    1.01
    Activations Density 1.922%

    No Known Activations