© 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. 6579
    Prev
    Next
    INDEX
    Explanations

    a variety of sentence fragments.

    oai_token-act-pair · gemini-2.0-flash

    positive, good

    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
     AssemblyCulture
    -0.64
    ErrorListener
    -0.62
    TagMode
    -0.58
     &$
    -0.56
    ciech
    -0.56
    MessageTagHelper
    -0.53
    AutoSize
    -0.52
    갓
    -0.52
     shewn
    -0.51
    Попис
    -0.51
    POSITIVE LOGITS
     positive
    1.06
     good
    0.92
    positive
    0.92
     pros
    0.88
     pro
    0.85
     Positive
    0.84
     positives
    0.82
    Positive
    0.82
     either
    0.80
    good
    0.80
    Activations Density 2.462%

    No Known Activations