© 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. 12079
    Prev
    Next
    INDEX
    Explanations

    words that are time oriented in many different ways

    oai_token-act-pair · gemini-2.0-flash

    swear 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_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
    UnknownFieldSet
    -0.73
     auffi
    -0.61
    didSet
    -0.60
     désolés
    -0.59
    CloseOperation
    -0.59
    setupUi
    -0.57
    ftagPool
    -0.56
     chofe
    -0.55
    DllImport
    -0.54
    CodeAttribute
    -0.53
    POSITIVE LOGITS
     fucking
    1.66
     fuck
    1.63
     damn
    1.60
     bloody
    1.58
    fucking
    1.57
    fuck
    1.55
     FUCK
    1.55
     damned
    1.52
     Fuck
    1.51
     Fucking
    1.51
    Activations Density 7.414%

    No Known Activations