© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13400
    Prev
    Next
    INDEX
    Explanations

    single-character tokens and numbers

    oai_token-act-pair · gemini-2.0-flash

    most

    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
    IsContent
    -0.67
    XmlAccessType
    -0.66
     Vikipedi
    -0.65
    XmlEnum
    -0.58
    DeleteBehavior
    -0.58
     виправивши
    -0.56
    StoreMessageInfo
    -0.54
     snippetHide
    -0.54
    StoryboardSegue
    -0.54
    aarrggbb
    -0.54
    POSITIVE LOGITS
     most
    3.86
    most
    3.30
    Most
    3.16
     Most
    3.11
     MOST
    2.67
    MOST
    2.39
     moft
    2.14
     moſt
    1.93
     meest
    1.69
    最も
    1.26
    Activations Density 14.550%

    No Known Activations