© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11398
    Prev
    Next
    INDEX
    Explanations

    snippets of windows forms C# code relating to a resizer panel on the left side of the form and mouse events

    oai_token-act-pair · gemini-2.0-flash

    unique or specialized terms

    np_token-act-pair-logits · gpt-4o-mini

    code/logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     to
    -0.56
    my
    -0.52
    )
    -0.50
     并
    -0.48
     my
    -0.48
     _,
    -0.47
     hàn
    -0.45
    kki
    -0.45
     for
    -0.45
    ?
    -0.45
    POSITIVE LOGITS
    Rujuakan
    0.89
     ་་
    0.77
     externi
    0.76
     ―――――
    0.75
    ſelves
    0.75
     Efq
    0.73
    AccessorTable
    0.73
     Walkover
    0.73
     Theſe
    0.73
     ſind
    0.72
    Activations Density 4.391%

    No Known Activations