© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14300
    Prev
    Next
    INDEX
    Explanations

    references to authors or people's names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     P
    -0.61
    P
    -0.50
    ">//
    -0.50
     C
    -0.45
    copg
    -0.44
     B
    -0.43
    Einzelnachweise
    -0.43
     R
    -0.42
    jaman
    -0.41
    edy
    -0.41
    POSITIVE LOGITS
     Efq
    0.76
     وتسجيلات
    0.69
     wireType
    0.69
    UnsafeEnabled
    0.67
    JspWriter
    0.66
    RetentionPolicy
    0.66
     propOrder
    0.64
    DockStyle
    0.64
    BibitemShut
    0.61
    MIDDLEWARE
    0.60
    Activations Density 2.563%

    No Known Activations