© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5855
    Prev
    Next
    INDEX
    Explanations

    words indicating possession or association, and words expressing skepticism or dedication

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    jectures
    -0.75
     themselves
    -0.73
     are
    -0.72
    awtextra
    -0.72
    ednesdays
    -0.68
    reactstrap
    -0.67
    chka
    -0.65
    iastical
    -0.65
    athread
    -0.65
    addPreferredGap
    -0.64
    POSITIVE LOGITS
    was
    0.58
    wasn
    0.58
     Wasn
    0.49
     Référence
    0.47
     wasn
    0.45
     estrat
    0.44
    ItemBackground
    0.43
    wouldn
    0.42
    Bref
    0.42
     popolazione
    0.41
    Activations Density 1.735%

    No Known Activations