© 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. 5563
    Prev
    Next
    INDEX
    Explanations

    the word "offset" and words that are often near it, such as "pixels" and "regular"

    oai_token-act-pair · gemini-2.0-flash

    offset

    np_max-act · 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
     déchir
    -1.41
     feroit
    -1.37
     Monfieur
    -1.32
    seamnă
    -1.30
     ainfi
    -1.30
     pleaſure
    -1.29
     pouvoit
    -1.27
     vectorielles
    -1.26
     myſelf
    -1.26
     itſelf
    -1.25
    POSITIVE LOGITS
    '
    0.77
     $\
    0.67
     
    0.63
    i
    0.62
    3
    0.61
    ↵
    0.60
     la
    0.59
     -
    0.58
    1
    0.56
    :
    0.56
    Activations Density 2.213%

    No Known Activations