© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8439
    Prev
    Next
    INDEX
    Explanations

    the word "fall" and other seemingly random words in its context.

    oai_token-act-pair · gemini-2.0-flash

    fall

    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
     poffible
    -0.77
     pleaſure
    -0.76
     ſtate
    -0.75
     fevere
    -0.73
     reaſon
    -0.69
     raiſ
    -0.69
     ſte
    -0.66
    DEPORTES
    -0.66
     ſtre
    -0.66
    енча
    -0.66
    POSITIVE LOGITS
    RenderAtEndOf
    0.83
    CloseOperation
    0.62
    RotationOrder
    0.59
     odeur
    0.57
    RectangleBorder
    0.57
     shoving
    0.57
    ValueGenerated
    0.54
    AnimationsModule
    0.54
     shoved
    0.53
    SetBool
    0.52
    Activations Density 1.820%

    No Known Activations