© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13700
    Prev
    Next
    INDEX
    Explanations

    sentences related to making and purchasing bags, particularly on Etsy.

    oai_token-act-pair · gemini-2.0-flash

    Sewing and crafting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    WaitGroup
    -0.58
     tightness
    -0.52
    IntoConstraints
    -0.51
     uiter
    -0.46
     Barbar
    -0.44
     traseiro
    -0.44
    Typ
    -0.43
     linkovi
    -0.43
    raseña
    -0.43
    RelativeTo
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.64
     ComVisible
    0.60
     متعلقه
    0.60
    UnsafeEnabled
    0.60
    AccessorTable
    0.59
    UnitTesting
    0.57
    StructEnd
    0.57
     springfox
    0.56
     reversible
    0.56
    autaire
    0.56
    Activations Density 3.098%

    No Known Activations