© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3025
    Prev
    Next
    INDEX
    Explanations

    words and themes related to social structures and human characteristics

    oai_token-act-pair · gemini-2.0-flash

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    sizeCache
    -0.79
    دانشنامهٔ
    -0.75
    transQ
    -0.75
    NewUrlParser
    -0.74
     Италијани
    -0.73
     PopupWindow
    -0.71
    InjectAttribute
    -0.63
    findpost
    -0.62
    IsMutable
    -0.60
     <=",
    -0.59
    POSITIVE LOGITS
     dis
    0.45
     лежит
    0.44
    اديم
    0.44
     سنت
    0.42
    DoubleQuotes
    0.41
    Atoi
    0.41
    <?>>
    0.41
    VersionUID
    0.40
    inence
    0.40
    services
    0.40
    Activations Density 3.601%

    No Known Activations