© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6654
    Prev
    Next
    INDEX
    Explanations

    relative ordinals such as "each", "first", "second", "third", and "every".

    oai_token-act-pair · gemini-2.0-flash

    steps in a process

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    tagHelperRunner
    -0.94
     ujednoznacz
    -0.84
     firſt
    -0.84
     propOrder
    -0.83
     first
    -0.81
    ImageContext
    -0.81
    PerformLayout
    -0.79
     betweenstory
    -0.78
    ItemBackground
    -0.76
     ModelExpression
    -0.75
    POSITIVE LOGITS
     assolu
    0.45
    ńskich
    0.43
     Full
    0.43
     P
    0.43
     libre
    0.43
    scriptcase
    0.41
     medesimo
    0.41
     Top
    0.41
     рождения
    0.39
    httpd
    0.39
    Activations Density 2.737%

    No Known Activations