© 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. 5978
    Prev
    Next
    INDEX
    Explanations

    words or phrases concerning illegal or prescription drugs

    oai_token-act-pair · gemini-2.0-flash

    drug

    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
     BrowserModule
    -0.55
    QMetaType
    -0.52
     xlink
    -0.48
    ViewData
    -0.48
     ivelany
    -0.47
    osoba
    -0.47
     Whiting
    -0.46
    colgroup
    -0.46
     FetchType
    -0.45
     lenker
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.65
    CppMethod
    0.62
    endpush
    0.59
     kasarigan
    0.59
    حياتها
    0.57
     Normdatei
    0.55
     zuges
    0.53
    scriptcase
    0.50
    ducks
    0.49
    vosť
    0.48
    Activations Density 6.017%

    No Known Activations