© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9937
    Prev
    Next
    INDEX
    Explanations

    code snippets or documentation related to URLs, specifically GitHub Raw URLs and Deno Land URLs, possibly for parsing or validation purposes.

    oai_token-act-pair · gemini-2.0-flash

    code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    migrationBuilder
    -1.15
    Datuak
    -1.13
    AndEndTag
    -1.05
     myſelf
    -0.91
    Бахар
    -0.91
    ագրություններ
    -0.86
     ujednoznacz
    -0.85
    extAlignment
    -0.84
     themſelves
    -0.83
    ChildScrollView
    -0.83
    POSITIVE LOGITS
     &
    0.63
    ,
    0.61
    ↵
    0.58
     |
    0.57
     
    0.54
    ]
    0.54
     =
    0.53
    0.52
    )
    0.52
    ↵↵
    0.52
    Activations Density 4.682%

    No Known Activations