© 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. 7173
    Prev
    Next
    INDEX
    Explanations

    phrases related to news broadcasting

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'Squ' or 'Mid'

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

    news and media

    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
    Rüyada
    -0.62
    mergeFrom
    -0.58
    autoreleasepool
    -0.57
    oa̍t
    -0.56
    ьаж
    -0.56
    formats
    -0.56
    IntoConstraints
    -0.55
     betweenstory
    -0.54
     Infórmanos
    -0.54
     gratuits
    -0.54
    POSITIVE LOGITS
    LElement
    0.50
     Squ
    0.49
     squ
    0.49
     Mid
    0.46
    لينكات
    0.45
    τ
    0.45
    Squ
    0.44
    hru
    0.43
     متعلقه
    0.42
     FF
    0.42
    Activations Density 0.513%

    No Known Activations