© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4284
    Prev
    Next
    INDEX
    Explanations

    code snippets, email addresses, variable assignments, and other programming-related text

    oai_token-act-pair · gemini-2.0-flash

    math/technical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    NUMX
    -0.79
     XNUMX
    -0.75
     
    -0.74
     purpoſe
    -0.74
     diſt
    -0.73
     NgModule
    -0.73
     raiſ
    -0.72
     
    -0.72
     myſelf
    -0.71
     ―――――
    -0.71
    POSITIVE LOGITS
    additive
    0.48
    lattice
    0.47
    raster
    0.44
    voxel
    0.43
    affine
    0.43
    isometric
    0.43
    convex
    0.43
    neuron
    0.43
    histogram
    0.42
    ada
    0.42
    Activations Density 9.857%

    No Known Activations