© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1519
    Prev
    Next
    INDEX
    Explanations

    code snippets dealing with a visualizer, keyboard input, and media playback (pause, scrub, advance)

    oai_token-act-pair · gemini-2.0-flash

    isPlaying, pause

    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
    Portale
    -0.75
     Gaut
    -0.67
    GIVEREF
    -0.62
     chiave
    -0.59
    matchCondition
    -0.59
    الإنجليزية
    -0.59
     للاسماء
    -0.57
    PyExc
    -0.57
     rispondere
    -0.56
     féminine
    -0.56
    POSITIVE LOGITS
    SourceChecksum
    0.57
     ongoing
    0.56
     Ongoing
    0.55
    ')['
    0.54
     started
    0.53
    ongoing
    0.53
     commenced
    0.52
     externi
    0.48
    เร็
    0.47
    )['
    0.47
    Activations Density 1.770%

    No Known Activations