© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3048
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities and fashion designers, along with potentially some financial numbers or dates, possibly related to news articles.

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    fashion models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ImageContext
    -0.77
    Datuak
    -0.76
    WriteAttribute
    -0.72
    Fashion
    -0.68
    CloseOperation
    -0.66
     Dressing
    -0.64
    AnchorStyles
    -0.63
    LayoutPanel
    -0.63
     robes
    -0.61
     FASHION
    -0.61
    POSITIVE LOGITS
    arschijnlijk
    0.52
    EndGlobalSection
    0.49
     olun
    0.48
    Jeografia
    0.47
    <bos>
    0.46
    っこう
    0.45
    UCKY
    0.44
    oa̍t
    0.43
     ponú
    0.43
    evos
    0.43
    Activations Density 0.805%

    No Known Activations