© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2889
    Prev
    Next
    INDEX
    Explanations

    words related to style or trimming or edges

    oai_token-act-pair · gemini-2.0-flash

    edging

    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
     يتيمه
    -1.09
    AddTagHelper
    -0.96
     snippetHide
    -0.96
    Tembelea
    -0.93
     Allociné
    -0.93
     تانيه
    -0.92
    OGND
    -0.92
    TagMode
    -0.91
    IsContent
    -0.91
    Personendaten
    -0.88
    POSITIVE LOGITS
    단
    0.38
    string
    0.36
     عب
    0.36
    ~
    0.35
     string
    0.35
     bella
    0.35
    ～
    0.34
    Commentary
    0.34
     N
    0.33
    logi
    0.33
    Activations Density 0.724%

    No Known Activations