© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10300
    Prev
    Next
    INDEX
    Explanations

    a variety of numbers, especially those found in categorical or enumerated data such as experimental results

    oai_token-act-pair · gemini-2.0-flash

    foreign language or technical terms

    np_token-act-pair-logits · gpt-4o-mini

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AddTagHelper
    -0.56
     transfieras
    -0.53
     ModelExpression
    -0.48
    енча
    -0.46
    A
    -0.46
     Baillargeon
    -0.45
    icher
    -0.43
    Captor
    -0.43
    ".
    -0.42
    principalColumn
    -0.42
    POSITIVE LOGITS
     الحره
    0.77
     InputDecoration
    0.69
     محفوظة
    0.63
     nhiêu
    0.60
     recevez
    0.57
     credere
    0.56
    amaged
    0.56
    原始内容存档于
    0.56
     reç
    0.55
    varande
    0.55
    Activations Density 3.663%

    No Known Activations