© 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. 3289
    Prev
    Next
    INDEX
    Explanations

    C code with hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    the presence of the digit "0" or variations of it

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

    =

    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
    SpringBootTest
    -0.70
    vastatin
    -0.57
    UpInside
    -0.54
     cfs
    -0.54
     مشين
    -0.51
    listo
    -0.50
     okazji
    -0.50
     通販
    -0.50
     Hannibal
    -0.50
    Péri
    -0.49
    POSITIVE LOGITS
     zero
    0.73
     يتيمه
    0.69
     Zero
    0.66
    ０
    0.66
    Zero
    0.65
    ########.
    0.63
    0
    0.62
    zero
    0.61
     ۰
    0.58
    ResumeLayout
    0.57
    Activations Density 3.960%

    No Known Activations