© 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. 9829
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly used when asking for or giving help with programming problems.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "write"

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

    writing

    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
     noten
    -0.49
     ressort
    -0.45
     Projection
    -0.45
    󠁢
    -0.45
     saites
    -0.43
     rimb
    -0.43
     spreken
    -0.41
     projection
    -0.40
    靡
    -0.40
    rz
    -0.40
    POSITIVE LOGITS
     writing
    1.70
     written
    1.50
     write
    1.50
     wrote
    1.45
    writing
    1.44
     Writing
    1.41
    Writing
    1.41
     writes
    1.31
     Write
    1.30
    written
    1.27
    Activations Density 3.318%

    No Known Activations