© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14989
    Prev
    Next
    INDEX
    Explanations

    words related to a change in state, movement, or quantity, often with the word "down".

    oai_token-act-pair · gemini-2.0-flash

    Change, movement, or state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    -------------</
    -0.51
    aktur
    -0.49
     come
    -0.49
    ViewFeatures
    -0.48
     ModelExpression
    -0.46
    Vidite
    -0.44
     Efe
    -0.44
    ombie
    -0.43
    horloge
    -0.43
     venons
    -0.43
    POSITIVE LOGITS
    anskje
    0.61
    intios
    0.59
    \}=
    0.56
    )";
    
    0.55
     GenerationType
    0.55
    TargetException
    0.54
    》.
    0.53
    runApp
    0.53
    KEYCODE
    0.53
     Waray
    0.52
    Activations Density 0.815%

    No Known Activations