© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12055
    Prev
    Next
    INDEX
    Explanations

    description of objects and their small features

    oai_token-act-pair · gemini-2.0-flash

    hanging, unloading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    mişti
    -0.59
     SIZE
    -0.53
     size
    -0.53
    SharedCtor
    -0.53
     INTERESAR
    -0.52
    pidou
    -0.52
     Sizes
    -0.51
    saurus
    -0.49
     Lumière
    -0.49
    findpost
    -0.48
    POSITIVE LOGITS
    AutoScale
    0.62
    DeleteBehavior
    0.59
     aload
    0.54
    RenderAtEndOf
    0.54
     &___
    0.54
     noires
    0.53
    posedge
    0.51
    Carriera
    0.51
     bears
    0.51
    contentLoaded
    0.49
    Activations Density 14.304%

    No Known Activations