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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12280
    Prev
    Next
    INDEX
    Explanations

    words that appear to be nonsensical.

    oai_token-act-pair · gemini-2.0-flash

    French words

    np_max-act-logits · 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
     I
    -0.91
     English
    -0.87
     American
    -0.85
     North
    -0.81
     New
    -0.79
     South
    -0.78
     Jan
    -0.77
     Android
    -0.77
     IV
    -0.76
     May
    -0.76
    POSITIVE LOGITS
     dévelo
    0.62
     élas
    0.62
     étoit
    0.61
     feroit
    0.59
     auroit
    0.58
     pouvoit
    0.57
     étoient
    0.56
     obé
    0.56
     poussière
    0.55
     nettoy
    0.54
    Activations Density 26.805%

    No Known Activations