© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5502
    Prev
    Next
    INDEX
    Explanations

    code-like and technical words, especially related to the field of cryptography or the Kubernetes API

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    spender
    -0.92
     HasFactory
    -0.78
     समीक्षाओं
    -0.75
    (!__
    -0.73
     GetEnumerator
    -0.70
     ProtoMessage
    -0.68
    FieldBuilder
    -0.67
    })*/
    -0.66
    queryInterface
    -0.66
     esternos
    -0.66
    POSITIVE LOGITS
     stanovnika
    0.46
     loyal
    0.45
    花板
    0.45
    G
    0.44
     over
    0.44
     maschile
    0.42
     colonias
    0.41
     origines
    0.41
    øya
    0.41
     propuesto
    0.41
    Activations Density 1.451%

    No Known Activations