© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14642
    Prev
    Next
    INDEX
    Explanations

    code-like text and HTML tags with ampersand-encoded non-breaking spaces.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    .
    -0.36
    Dir
    -0.36
    Predicate
    -0.34
    SELECTION
    -0.34
     Def
    -0.33
     def
    -0.33
     ואת
    -0.33
    ătă
    -0.33
    боры
    -0.33
    бора
    -0.33
    POSITIVE LOGITS
     Audiodateien
    0.94
    sidemargin
    0.88
    Tikang
    0.88
     Biôgrafia
    0.87
    AutoScaleMode
    0.84
    StoryboardSegue
    0.84
    Personensuche
    0.83
    oneofs
    0.83
    StructEnd
    0.82
    onViewCreated
    0.81
    Activations Density 2.802%

    No Known Activations