© 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. 4068
    Prev
    Next
    INDEX
    Explanations

    scientific notation and references to other publications

    oai_token-act-pair · gemini-2.0-flash

    last names

    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
     saites
    -0.77
    Personensuche
    -0.71
     ◄
    -0.71
     defaultstate
    -0.70
     للاسماء
    -0.69
     initComponents
    -0.68
     ExecuteAsync
    -0.67
    rungsseite
    -0.66
     مرئيه
    -0.66
       
    -0.65
    POSITIVE LOGITS
    kiewicz
    0.57
    hofer
    0.54
    kowski
    0.54
    zner
    0.54
    kovich
    0.52
    owiak
    0.51
    czuk
    0.50
    dorfer
    0.49
    zenberg
    0.49
    mayr
    0.48
    Activations Density 11.606%

    No Known Activations