© 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. 14131
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "layer," including modifiers like "underlying" and the use of the word in the context of layered systems.

    oai_token-act-pair · gemini-2.0-flash

    Software/technical layers

    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
     Layer
    -2.47
     layers
    -2.47
     layer
    -2.45
     Layers
    -2.39
    Layer
    -2.30
     LAYER
    -2.25
    layer
    -2.25
    layers
    -2.14
    Layers
    -2.13
     layered
    -2.08
    POSITIVE LOGITS
    Abit
    0.50
    ViewFeatures
    0.44
     expédié
    0.42
     programmet
    0.41
     cherchés
    0.39
    новниш
    0.39
     кӀош
    0.39
    ControllerAdvice
    0.39
    LabelTagHelper
    0.37
    ⓧ
    0.37
    Activations Density 1.365%

    No Known Activations