© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1397
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to customization, adaptation, and modification.

    oai_token-act-pair · gemini-2.0-flash

    Customization and tailoring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     consultato
    -0.74
     propOrder
    -0.69
    Przypisy
    -0.66
    )|^{
    -0.66
    SpringBootTest
    -0.64
    DllImport
    -0.61
     Ronde
    -0.59
    JsonPropertyName
    -0.59
    orianCalendar
    -0.59
     unknownFields
    -0.59
    POSITIVE LOGITS
    studi
    0.59
    holdt
    0.45
    ższy
    0.43
    indrical
    0.42
     Prof
    0.41
    HQ
    0.41
    bone
    0.41
    holdet
    0.40
     váy
    0.40
     Bar
    0.40
    Activations Density 2.734%

    No Known Activations