© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    non-English words or specific coding syntax

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

    Code snippets

    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
     nakalista
    -0.79
     ویکی‌پدی
    -0.69
    otum
    -0.54
     protoimpl
    -0.53
    libft
    -0.51
    expandindo
    -0.51
    quante
    -0.50
    帖最后由
    -0.48
    گاب
    -0.47
    >[]
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.65
     AssemblyTitle
    0.54
    śle
    0.53
    batore
    0.51
    Gweler
    0.51
    Tazama
    0.49
    ⓧ
    0.48
     douce
    0.48
     symbolism
    0.47
     føl
    0.47
    Activations Density 2.963%

    No Known Activations