© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5493
    Prev
    Next
    INDEX
    Explanations

    questions in a question/answer format

    oai_token-act-pair · gemini-2.0-flash

    questions

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

    Q

    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
    Q
    -1.40
    q
    -1.34
     q
    -1.20
     Q
    -1.18
    Ｑ
    -0.89
    Qs
    -0.81
    qar
    -0.74
    qai
    -0.73
    𝑞
    -0.73
    ｑ
    -0.72
    POSITIVE LOGITS
    XmlAccessorType
    0.60
    出版年
    0.56
     متعلقه
    0.44
     @"/
    0.44
    дох
    0.43
    ut
    0.43
    bert
    0.42
     transfieras
    0.42
    ball
    0.41
     īpa
    0.41
    Activations Density 0.871%

    No Known Activations