© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 886
    Prev
    Next
    INDEX
    Explanations

    code snippets and fragments of computer language

    oai_token-act-pair · gemini-2.0-flash

    software/programming contexts

    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
     européens
    -0.65
     étrangères
    -0.63
     internationaux
    -0.63
     communs
    -0.62
     démocr
    -0.62
     étrangère
    -0.62
     européennes
    -0.61
     étrangers
    -0.60
     noires
    -0.60
     humaines
    -0.58
    POSITIVE LOGITS
    udert
    0.56
     Nun
    0.55
     Und
    0.55
    enderror
    0.54
     Tup
    0.54
    CodeAttribute
    0.54
    yt
    0.53
     aback
    0.52
    :][
    0.52
     Thug
    0.52
    Activations Density 5.020%

    No Known Activations