© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8859
    Prev
    Next
    INDEX
    Explanations

    mentions of activity or actions that have happened in a recent time frame

    oai_token-act-pair · gemini-2.0-flash

    blog posts and mentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    GOTREF
    -0.68
    IActionResult
    -0.67
    WebElementEntity
    -0.66
    MENAFN
    -0.64
    GEBURTSDATUM
    -0.63
    Hauptartikel
    -0.60
    scrapy
    -0.60
     виправивши
    -0.60
    
    -0.60
     resourceCulture
    -0.59
    POSITIVE LOGITS
    ArgsConstructor
    0.57
    ExtendWith
    0.46
    offices
    0.44
     assoluto
    0.44
     oscilloscope
    0.43
     valmis
    0.41
    klere
    0.40
     subjected
    0.40
     synthase
    0.39
     ')'
    0.39
    Activations Density 2.137%

    No Known Activations