© 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. 3965
    Prev
    Next
    INDEX
    Explanations

    strings of characters that look like scientific notation and statistics

    oai_token-act-pair · gemini-2.0-flash

    scientific/statistical analysis

    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
    iertamente
    -0.44
    '/',
    -0.44
    chemise
    -0.40
     contente
    -0.39
    taget
    -0.39
    Attached
    -0.39
     Rohr
    -0.39
    ranza
    -0.39
     parma
    -0.38
     GENERATED
    -0.38
    POSITIVE LOGITS
     beginnetje
    0.72
     morbidity
    0.66
    thâu
    0.64
    Demografia
    0.63
     AssemblyCompany
    0.62
    ftagPool
    0.60
     nakalista
    0.60
     فريبيس
    0.60
    InstanceState
    0.60
    jstor
    0.60
    Activations Density 40.749%

    No Known Activations