© 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. 9156
    Prev
    Next
    INDEX
    Explanations

    text related to the act of creative writing or drawing.

    oai_token-act-pair · gemini-2.0-flash

    prompts for creativity or inquiry

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

    Tips and strategies

    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
     ostavi
    -0.57
     onCancelled
    -0.54
     оно
    -0.52
    ρίς
    -0.50
    ništ
    -0.49
    zeba
    -0.48
     Catawiki
    -0.48
    fony
    -0.48
    CppCodeGen
    -0.48
    Varint
    -0.47
    POSITIVE LOGITS
     things
    0.68
     strategies
    0.65
     tips
    0.63
     CreateTagHelper
    0.63
     challenges
    0.59
     hints
    0.59
     stuff
    0.58
     questions
    0.57
     clues
    0.57
     examples
    0.57
    Activations Density 8.641%

    No Known Activations