© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14577
    Prev
    Next
    INDEX
    Explanations

    C++ code

    oai_token-act-pair · gemini-2.0-flash

    int

    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
    contentLoaded
    -1.00
     gambe
    -0.71
    AndroidJUnit
    -0.65
    tagHelperRunner
    -0.63
     iprot
    -0.60
     تضيفلها
    -0.60
    LookAnd
    -0.57
     Infórmanos
    -0.57
     condizione
    -0.56
    ########.
    -0.55
    POSITIVE LOGITS
    yní
    0.53
     Siegfried
    0.47
    AnchorTagHelper
    0.47
    acamata
    0.47
    okai
    0.47
    OrBuilder
    0.46
     ¦
    0.45
    devise
    0.45
     seta
    0.44
    Izvori
    0.44
    Activations Density 2.395%

    No Known Activations