© 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. 7844
    Prev
    Next
    INDEX
    Explanations

    references to the news media, especially in relation to political power

    oai_token-act-pair · gemini-2.0-flash

    terms related to media and newspapers

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

    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
    stateProvider
    -0.76
     disambiguazione
    -0.67
     Италијани
    -0.58
    Бахар
    -0.51
     Вікі
    -0.49
    principalColumn
    -0.48
    Filmography
    -0.48
    Catatan
    -0.47
     numberOfRows
    -0.47
     CONCEP
    -0.47
    POSITIVE LOGITS
     media
    1.59
     newspapers
    1.55
     newspaper
    1.51
    media
    1.34
     press
    1.33
     Newspapers
    1.25
    newspaper
    1.24
     Media
    1.23
    Media
    1.23
     presse
    1.21
    Activations Density 2.040%

    No Known Activations