© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7169
    Prev
    Next
    INDEX
    Explanations

    mentions of positive abstract concepts, often including "the" and a word with a positive connotation.

    oai_token-act-pair · gemini-2.0-flash

    power, magic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    blogspot
    -0.44
    lv
    -0.44
     atti
    -0.43
    toBeDefined
    -0.41
    minecraftforge
    -0.40
    chables
    -0.40
    ctil
    -0.39
    ACTS
    -0.38
     sien
    -0.38
    kusen
    -0.38
    POSITIVE LOGITS
    URLException
    0.86
     تضيفلها
    0.85
     power
    0.83
     beauty
    0.79
     estekak
    0.77
    MemoryWarning
    0.77
     kracht
    0.77
     potere
    0.76
    power
    0.75
     magic
    0.75
    Activations Density 0.734%

    No Known Activations