© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3843
    Prev
    Next
    INDEX
    Explanations

    words describing physical sensations, especially related to sound and touch, and mechanical malfunctions

    oai_token-act-pair · gemini-2.0-flash

    sounds/noises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    FormTagHelper
    -0.75
    ("]");
    -0.68
     ViewGroup
    -0.65
    endregion
    -0.65
     autorytatywna
    -0.62
     المعيارى
    -0.60
    ]--;
    -0.59
    piram
    -0.57
     Pila
    -0.57
    hObject
    -0.57
    POSITIVE LOGITS
    ftagPool
    0.59
     وتسجيلات
    0.57
     بيها
    0.48
     utafitiHapana
    0.47
     مواليد
    0.46
     consultato
    0.45
     ninguno
    0.43
    égek
    0.43
     indisponible
    0.43
    :+:
    0.43
    Activations Density 0.884%

    No Known Activations