© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10265
    Prev
    Next
    INDEX
    Explanations

    sentences about a specific person and their accomplishments

    oai_token-act-pair · gemini-2.0-flash

    foreign 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     disambiguazione
    -0.98
    complexContent
    -0.85
     createState
    -0.79
     useStyles
    -0.79
    NewUrlParser
    -0.77
     فريبيس
    -0.73
    PropertyChanging
    -0.71
    FormTagHelper
    -0.71
    SharedDtor
    -0.71
     protoimpl
    -0.71
    POSITIVE LOGITS
    ूत
    0.49
     mer
    0.43
     дуб
    0.40
    agas
    0.40
    plo
    0.39
    digen
    0.39
    emes
    0.39
    kat
    0.39
    dist
    0.39
    ident
    0.38
    Activations Density 0.386%

    No Known Activations