© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 477
    Prev
    Next
    INDEX
    Explanations

    terms related to local television news programming and broadcasting schedules.

    oai_token-act-pair · gemini-2.0-flash

    programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AndEndTag
    -0.84
     >=",
    -0.70
    PerformLayout
    -0.70
    noons
    -0.69
     Савезне
    -0.69
    webElementXpaths
    -0.63
    InjectAttribute
    -0.63
     تانيه
    -0.60
     cherchés
    -0.60
     occasions
    -0.59
    POSITIVE LOGITS
    habitants
    0.49
     đích
    0.48
    ínű
    0.47
    peda
    0.47
     īpa
    0.46
    ares
    0.45
    صاص
    0.45
     vē
    0.44
     preliminary
    0.44
     متعلقه
    0.44
    Activations Density 11.078%

    No Known Activations