© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13024
    Prev
    Next
    INDEX
    Explanations

    names that begin with the letters 'Ry', 'Ky', or 'Dy'

    oai_token-act-pair · gemini-2.0-flash

    two-letter tokens ending in 'y'

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.61
    ValueGeneration
    -0.60
     Lordships
    -0.57
     typelib
    -0.56
    awaiter
    -0.54
    andescent
    -0.53
     facie
    -0.52
    contentLoaded
    -0.52
    MigrationBuilder
    -0.52
    VersionUID
    -0.52
    POSITIVE LOGITS
     passés
    0.50
     jouets
    0.49
     Unavailable
    0.48
     rodea
    0.47
     réussite
    0.46
     rêves
    0.46
     δὲ
    0.46
     fermés
    0.45
     religieuses
    0.44
    nten
    0.44
    Activations Density 1.925%

    No Known Activations