© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13273
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'forced' or the word 'patch'

    oai_token-act-pair · gemini-2.0-flash

    forced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     vertes
    -0.81
    esine
    -0.65
     parís
    -0.65
     dedans
    -0.62
    )}</
    -0.60
     méri
    -0.60
    ándolos
    -0.59
     estrutura
    -0.59
     blanches
    -0.57
    isUser
    -0.57
    POSITIVE LOGITS
     المعيارى
    0.83
    makeConstraints
    0.81
    IntoConstraints
    0.73
     autorytatywna
    0.69
     surla
    0.68
    SequentialGroup
    0.65
     consultato
    0.65
    ConstraintMaker
    0.64
     Paglinawan
    0.63
    CloseOperation
    0.63
    Activations Density 1.193%

    No Known Activations