© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4190
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to official processes, decisions, or outcomes

    oai_token-act-pair · gemini-2.0-flash

    agreement and action

    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
    __':
    -0.64
    reszcie
    -0.63
     Réponses
    -0.58
    <bos>
    -0.57
    Initializable
    -0.57
    Tikang
    -0.56
    finally
    -0.56
    onViewCreated
    -0.54
     مرئيه
    -0.54
    hésite
    -0.54
    POSITIVE LOGITS
     resourceCulture
    0.62
    帖最后由
    0.60
    tagHelperRunner
    0.57
     attribution
    0.53
    GUILayout
    0.52
    mise
    0.52
    brot
    0.52
    entire
    0.50
     Ooster
    0.50
    InSection
    0.50
    Activations Density 1.785%

    No Known Activations