© 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. 4227
    Prev
    Next
    INDEX
    Explanations

    words related to rules and support tickets, as well as pronouns.

    oai_token-act-pair · gemini-2.0-flash

    Speech/Communication

    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
     autorytatywna
    -0.62
    hoeddwyd
    -0.59
    Gambas
    -0.58
     kasarigan
    -0.57
     JSTOR
    -0.54
    eryllium
    -0.54
    참고
    -0.52
    StoreMessageInfo
    -0.50
    ReusableCell
    -0.49
     dirait
    -0.49
    POSITIVE LOGITS
    >[]
    0.56
     تانيه
    0.54
     CYTHON
    0.52
    uyer
    0.50
    haku
    0.47
    ForValue
    0.47
    ThroughAttribute
    0.47
    tovers
    0.47
     HON
    0.46
    DockStyle
    0.45
    Activations Density 7.711%

    No Known Activations