© 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. 6070
    Prev
    Next
    INDEX
    Explanations

    instances of the first person, especially when making a point or expressing a belief

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming references

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

    code/errors

    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
    -0.54
    <table>
    -0.52
     well
    -0.51
    (|
    -0.50
     dir
    -0.50
    éc
    -0.50
    бри
    -0.49
    >{"
    -0.49
    raya
    -0.49
    <blockquote>
    -0.48
    POSITIVE LOGITS
    WriteBarrier
    0.68
    FormTagHelper
    0.67
    NOPQRST
    0.65
    LabelTagHelper
    0.64
     varandra
    0.63
    yntaxException
    0.61
     برانيه
    0.59
    μβρίου
    0.58
     comigo
    0.55
     ujednoznacz
    0.55
    Activations Density 2.262%

    No Known Activations