© 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. 9773
    Prev
    Next
    INDEX
    Explanations

    angle brackets and text related to legal documents

    oai_token-act-pair · gemini-2.0-flash

    ><

    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
    SequentialGroup
    -0.83
    Przypisy
    -0.53
    segundo
    -0.46
    Бележки
    -0.46
    তথ্যসূত্র
    -0.45
    Välislingid
    -0.45
     dataSnapshot
    -0.45
    __((
    -0.44
     pointed
    -0.43
    日閲覧
    -0.43
    POSITIVE LOGITS
    IVEREF
    0.66
     AssemblyTitle
    0.63
     Administrativna
    0.62
    TableAdapter
    0.60
    IGENCE
    0.60
    новниш
    0.60
    UrlResolution
    0.60
     Exacts
    0.59
     BrowserModule
    0.59
    CloseOperation
    0.56
    Activations Density 1.159%

    No Known Activations