© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14346
    Prev
    Next
    INDEX
    Explanations

    code snippets and language syntax

    oai_token-act-pair · gemini-2.0-flash

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    imb
    -0.46
    히
    -0.44
    SL
    -0.44
     F
    -0.42
    !
    -0.42
     maiores
    -0.41
    :
    -0.40
    medium
    -0.40
     He
    -0.40
    SV
    -0.40
    POSITIVE LOGITS
     itſelf
    1.16
     myſelf
    1.16
     themſelves
    1.02
     raiſ
    0.95
     ſever
    0.91
     houſe
    0.90
     whoſe
    0.88
     reaſon
    0.88
     uſed
    0.87
     neceff
    0.83
    Activations Density 8.615%

    No Known Activations