© 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. 9937
    Prev
    Next
    INDEX
    Explanations

    code snippets with routes

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     InputDecoration
    -0.66
    webElementXpaths
    -0.58
    ㅗ
    -0.56
    TestBed
    -0.52
     Meksiku
    -0.52
    ributes
    -0.51
    oded
    -0.48
    OrBuilder
    -0.48
     ListTile
    -0.47
    endregion
    -0.47
    POSITIVE LOGITS
    ItemBackground
    0.73
    RenderAtEndOf
    0.64
     Baillargeon
    0.60
     समीक्षक
    0.59
    #+#
    0.53
     normaux
    0.53
    libft
    0.51
     Soyez
    0.50
     écoute
    0.49
     Offisielt
    0.48
    Activations Density 0.289%

    No Known Activations