© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4372
    Prev
    Next
    INDEX
    Explanations

    Danish words or phrases, possibly movie/song titles

    oai_token-act-pair · gemini-2.0-flash

    pi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AddHtmlAttribute
    -0.83
    AndEndTag
    -0.76
    Personendaten
    -0.72
    Diwedd
    -0.67
     onPostExecute
    -0.67
    webElementXpaths
    -0.67
     Edelman
    -0.60
    TagMode
    -0.60
     PLAINTIFF
    -0.58
     Racer
    -0.57
    POSITIVE LOGITS
    tanleria
    0.50
    PointerException
    0.46
     gärna
    0.46
    таратура
    0.44
    ]<<"
    0.42
    Georges
    0.41
     childs
    0.41
     pels
    0.40
    ageable
    0.40
    lasts
    0.40
    Activations Density 0.411%

    No Known Activations