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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5713
    Prev
    Next
    INDEX
    Explanations

    tables

    oai_token-act-pair · gemini-2.0-flash

    technical terms or keywords in software development

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

    Korean dramas

    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
    RefNanny
    -0.57
    expiresIn
    -0.53
    出版年
    -0.52
    adera
    -0.50
    FormTagHelper
    -0.49
    photobucket
    -0.49
    spectos
    -0.49
    帖最后由
    -0.48
    imageshack
    -0.48
    basicConfig
    -0.48
    POSITIVE LOGITS
     оригіналу
    0.83
    usercontent
    0.57
     MenuView
    0.56
     AppCompatTheme
    0.54
    NullCheck
    0.53
    曖昧さ回避
    0.53
    featureID
    0.52
    testify
    0.52
     group
    0.51
    cency
    0.51
    Activations Density 0.684%

    No Known Activations