© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12667
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and article titles.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     on
    -0.60
     about
    -0.52
     kasarigan
    -0.49
    EndProject
    -0.48
    HasAnnotation
    -0.48
     onSave
    -0.48
    //
    -0.48
    ISSN
    -0.48
     "..\..\..\
    -0.47
    WriteBarrier
    -0.47
    POSITIVE LOGITS
     Why
    0.90
    Why
    0.79
     Drapeau
    0.77
     varför
    0.73
     How
    0.71
     WHY
    0.71
     kaarangay
    0.69
     betweenstory
    0.69
    why
    0.68
     Warum
    0.67
    Activations Density 4.294%

    No Known Activations