© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9779
    Prev
    Next
    INDEX
    Explanations

    code snippets and structured data.

    oai_token-act-pair · gemini-2.0-flash

    Code/technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    WHEN
    -0.84
    WITH
    -0.80
    FROM
    -0.79
    HERE
    -0.76
     ABOUT
    -0.76
     Италијани
    -0.75
    MigrationBuilder
    -0.74
    NOW
    -0.73
    THAN
    -0.72
    WITHOUT
    -0.72
    POSITIVE LOGITS
     Sito
    0.52
     roulant
    0.51
    ysty
    0.49
     louer
    0.47
    MemoryWarning
    0.47
    "}}
    0.46
    ˏ
    0.45
    konomi
    0.45
     CiNii
    0.44
     fotografico
    0.44
    Activations Density 1.702%

    No Known Activations