© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9925
    Prev
    Next
    INDEX
    Explanations

    code snippets that use single-character variables and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms and expressions

    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
     leſs
    -0.72
    ########.
    -0.69
     greateſt
    -0.64
     fubject
    -0.63
     Monfieur
    -0.63
     pleaſure
    -0.63
    #![
    -0.62
     deſt
    -0.61
     poffible
    -0.61
     Majefty
    -0.61
    POSITIVE LOGITS
     surla
    0.51
     and
    0.47
     "
    0.44
     soutenu
    0.43
    المشاركات
    0.43
    帖最后由
    0.42
    </h3>
    0.42
    verifyException
    0.42
    UnknownFieldSet
    0.41
     EClass
    0.40
    Activations Density 1.871%

    No Known Activations