© 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. 11763
    Prev
    Next
    INDEX
    Explanations

    sentences about people that include details about their work and education

    oai_token-act-pair · gemini-2.0-flash

    Careers and roles

    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
     كومونز
    -0.63
     saites
    -0.63
     her
    -0.62
     AssemblyTitle
    -0.59
    :✨
    -0.58
    monials
    -0.56
    SharedCtor
    -0.54
    IVEREF
    -0.54
     createState
    -0.53
    IBOutlet
    -0.52
    POSITIVE LOGITS
     تضيفلها
    0.61
    dersfield
    0.55
    standers
    0.50
    aurait
    0.47
    WarningLevel
    0.46
    不知
    0.45
    }=-
    0.45
     abbiano
    0.44
    тьяна
    0.44
     подозре
    0.44
    Activations Density 5.230%

    No Known Activations