© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7524
    Prev
    Next
    INDEX
    Explanations

    words related to: development, frameworks, systems, organizations, relationships, healthcare, and data

    oai_token-act-pair · gemini-2.0-flash

    Programs and environments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ########.
    -0.62
     Baillargeon
    -0.56
    Gambas
    -0.51
    CppMethod
    -0.50
    Viitteet
    -0.50
    NewLabel
    -0.49
    __':
    -0.49
    complexType
    -0.49
    having
    -0.48
    Mutagenicity
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.57
     that
    0.56
     retrou
    0.50
     Chambres
    0.49
    ibia
    0.48
    TheGreat
    0.47
    ồng
    0.47
     departing
    0.46
     Dioxide
    0.45
    PyExc
    0.45
    Activations Density 8.049%

    No Known Activations