© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5353
    Prev
    Next
    INDEX
    Explanations

    What this neuron does is unclear. It seems to be picking up on various disparate things, including gambling-related terms and parts of an academic paper. It may recognize spam text

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ########.
    -0.59
    AddTagHelper
    -0.56
     defaultstate
    -0.51
    hoeddwyd
    -0.50
    styleable
    -0.49
    phosphat
    -0.48
    FontStyle
    -0.47
    BagLayout
    -0.46
    abetes
    -0.45
    httphttps
    -0.45
    POSITIVE LOGITS
    gius
    0.59
    Revenir
    0.53
    consulté
    0.51
    mui
    0.50
    Биография
    0.49
     dante
    0.49
    المكان
    0.49
    ("}");
    0.49
    তথ্যসূত্র
    0.49
    setSelection
    0.48
    Activations Density 0.467%

    No Known Activations