© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9163
    Prev
    Next
    INDEX
    Explanations

    words that describe types of professions and professional services and equipment

    oai_token-act-pair · gemini-2.0-flash

    therapies

    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
     beginnetje
    -0.71
    WebVitals
    -0.71
     '\\;'
    -0.69
     PLWABN
    -0.69
    ClientRect
    -0.66
    WriteTagHelper
    -0.65
     defaultstate
    -0.61
     للاسماء
    -0.61
     esboço
    -0.60
    ChromeDriver
    -0.59
    POSITIVE LOGITS
    AnchorStyles
    0.76
     therapeutic
    0.59
     religieuse
    0.58
     physiotherapy
    0.56
     therapy
    0.55
     Therapy
    0.54
    Therapeutic
    0.54
     religieuses
    0.53
     cardiaque
    0.52
     Therapeutic
    0.52
    Activations Density 10.427%

    No Known Activations