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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8556
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to stating facts and information

    oai_token-act-pair · gemini-2.0-flash

    complete sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ValueStyle
    -0.70
     Waray
    -0.54
    abestanden
    -0.52
    urator
    -0.50
    ArgsConstructor
    -0.50
    gameserver
    -0.49
     Мексичка
    -0.48
     DriverManager
    -0.48
    uría
    -0.48
    TestMethod
    -0.47
    POSITIVE LOGITS
    characteristic
    0.61
    asztal
    0.56
     IBOutlet
    0.54
    tvguidetime
    0.51
     SqlParameter
    0.51
    enumi
    0.51
    hofen
    0.50
    Autoritní
    0.50
    yny
    0.49
     ALONG
    0.48
    Activations Density 2.889%

    No Known Activations