© 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. 4036
    Prev
    Next
    INDEX
    Explanations

    words commonly used in descriptions of underwater photography and diving

    oai_token-act-pair · gemini-2.0-flash

    foreign 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
    writeField
    -0.73
    XmlAccessType
    -0.73
    orianCalendar
    -0.72
     &___
    -0.71
    hyrchwyd
    -0.66
    دانشنامهٔ
    -0.65
     препратки
    -0.62
    mobileqq
    -0.60
     تضيفلها
    -0.60
     thiệu
    -0.59
    POSITIVE LOGITS
     trajets
    0.51
    photobucket
    0.47
     devront
    0.43
    QUADS
    0.42
     ze
    0.42
    Si
    0.40
     senderos
    0.39
     rowspan
    0.39
     comunión
    0.39
     sanitaires
    0.39
    Activations Density 4.614%

    No Known Activations