© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10988
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially those related to measurements or identification numbers

    oai_token-act-pair · gemini-2.0-flash

    numerals

    np_max-act · gemini-2.0-flash

    numbers

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     виправивши
    -1.61
    ^(@)
    -1.49
     itſelf
    -1.45
    $.
    -1.38
    >\<^
    -1.37
    )");
    -1.37
    ikusbot
    -1.35
    __":
    -1.34
    NUMX
    -1.34
    '},
    -1.34
    POSITIVE LOGITS
    ↵
    1.10
    i
    0.99
    L
    0.95
    R
    0.95
    3
    0.94
     (
    0.94
    6
    0.93
    1
    0.92
    2
    0.92
    ,
    0.91
    Activations Density 1.793%

    No Known Activations