© 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. 5271
    Prev
    Next
    INDEX
    Explanations

    hexidecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    stylized or Unicode characters

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

    code and hex

    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
    sel
    -0.52
     e
    -0.52
     E
    -0.51
     test
    -0.51
     i
    -0.46
     on
    -0.46
    <em>
    -0.46
     si
    -0.45
     I
    -0.44
    test
    -0.44
    POSITIVE LOGITS
    
    0.94
     Theſe
    0.94
     Efq
    0.92
     itſelf
    0.90
     Reſ
    0.89
     raiſ
    0.87
     protoimpl
    0.86
     leaſt
    0.85
     Diſ
    0.84
     ſeveral
    0.83
    Activations Density 7.205%

    No Known Activations