© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12662
    Prev
    Next
    INDEX
    Explanations

    fully qualified names of packages, files, classes, and methods, especially in Java and Android code

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ArgsConstructor
    -0.66
     ويكيميديا
    -0.55
     kê
    -0.52
    centred
    -0.52
     IntPtr
    -0.51
     centre
    -0.50
    #+#
    -0.49
    govine
    -0.49
     centred
    -0.48
    centre
    -0.48
    POSITIVE LOGITS
     viață
    0.58
     uș
    0.57
    WriteAttribute
    0.55
     oraș
    0.55
    LLocation
    0.55
     urmă
    0.54
     maș
    0.53
     oamen
    0.52
    awtextra
    0.52
    ❋
    0.52
    Activations Density 2.168%

    No Known Activations