© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9475
    Prev
    Next
    INDEX
    Explanations

    the word "listen" and its derivations, as well as the word "enable."

    oai_token-act-pair · gemini-2.0-flash

    enable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     chev
    -0.53
    essoal
    -0.52
    TestingModule
    -0.50
    ścić
    -0.47
    Else
    -0.45
     Stoke
    -0.45
     Altri
    -0.45
    goto
    -0.44
     gæ
    -0.42
    żs
    -0.42
    POSITIVE LOGITS
     listen
    1.06
     listening
    1.04
     LISTEN
    1.02
     Listen
    0.98
    Listen
    0.95
     listens
    0.94
     LOOK
    0.94
     listened
    0.93
    listening
    0.93
     look
    0.91
    Activations Density 0.692%

    No Known Activations