© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1912
    Prev
    Next
    INDEX
    Explanations

    html or angular code related to iterating and displaying a list of musical categories and tags and seems to latch onto religious terms as well

    oai_token-act-pair · gemini-2.0-flash

    deleted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.63
     الرياضيه
    -0.57
    кономі
    -0.45
    indest
    -0.44
     Allen
    -0.41
    ể
    -0.40
    нави
    -0.40
     roman
    -0.39
    znál
    -0.39
    cos
    -0.39
    POSITIVE LOGITS
    tvguidetime
    0.93
    MemoryWarning
    0.82
     MainAxisSize
    0.79
    \{\\
    0.74
    脚注の使い方
    0.71
    دانشنامهٔ
    0.71
    ContentAsync
    0.69
     OnInit
    0.69
    invokeLater
    0.69
    __":
    0.68
    Activations Density 1.952%

    No Known Activations