© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10571
    Prev
    Next
    INDEX
    Explanations

    Latex or code snippets including symbols, letters and numbers

    oai_token-act-pair · gemini-2.0-flash

    Code, math, file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -0.44
    ADELPHIA
    -0.42
     Geografia
    -0.41
     estoppel
    -0.41
     botanist
    -0.40
     pyl
    -0.40
     WSU
    -0.39
    -0.38
     Babylonian
    -0.35
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    0.99
    transQ
    0.91
    AddTagHelper
    0.85
     يتيمه
    0.80
    BeginContext
    0.80
    RegressionTest
    0.79
     typelib
    0.77
    AndroidJUnit
    0.77
    verwijspagina
    0.76
    TRIBUN
    0.75
    Activations Density 0.844%

    No Known Activations