© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12781
    Prev
    Next
    INDEX
    Explanations

    words that relate to growth, addition, edits, and other terms denoting an increase

    oai_token-act-pair · gemini-2.0-flash

    expanded

    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
     expanded
    -1.50
     reduced
    -1.41
     improved
    -1.40
    reduced
    -1.39
     revised
    -1.37
     decreased
    -1.34
     renewed
    -1.34
     altered
    -1.31
     upgraded
    -1.31
     increased
    -1.30
    POSITIVE LOGITS
    ValueStyle
    0.59
    Personendaten
    0.57
     lượt
    0.56
     referrerpolicy
    0.55
    consulté
    0.54
     change
    0.52
     Geraadpleegd
    0.52
    led
    0.52
     '\\;'
    0.52
     faced
    0.51
    Activations Density 2.761%

    No Known Activations