© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15262
    Prev
    Next
    INDEX
    Explanations

    conversational text where the author is telling the reader what they will like or be able to do

    oai_token-act-pair · gemini-2.0-flash

    will

    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
    adaptiveStyles
    -0.66
     snippetHide
    -0.64
    ыгана
    -0.57
     lanka
    -0.57
    setVerticalGroup
    -0.57
    SBATCH
    -0.57
    tagHelper
    -0.56
     sorte
    -0.56
    complexContent
    -0.56
    autique
    -0.56
    POSITIVE LOGITS
    hyrchwyd
    0.49
     progrès
    0.47
     saisi
    0.45
     виправивши
    0.45
     fir
    0.44
     have
    0.43
    توض
    0.43
     rues
    0.43
     signé
    0.42
     réunis
    0.42
    Activations Density 1.679%

    No Known Activations