© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10730
    Prev
    Next
    INDEX
    Explanations

    words related to news media, writing, and reporting on events

    oai_token-act-pair · gemini-2.0-flash

    news/stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ainfi
    -1.20
     Monfieur
    -1.14
     acrylique
    -1.14
     Majefty
    -1.10
     Houſe
    -1.08
     feroit
    -1.02
     myſelf
    -1.02
     Efq
    -0.97
    ſelf
    -0.94
     auroit
    -0.94
    POSITIVE LOGITS
    <blockquote>
    0.68
    <i>
    0.66
    </i>
    0.66
    ніципалі
    0.58
     
    0.58
     favourites
    0.57
    ilisation
    0.57
    2
    0.56
    1
    0.55
    I
    0.54
    Activations Density 1.145%

    No Known Activations