© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5365
    Prev
    Next
    INDEX
    Explanations

    German words and phrases, particularly those related to government or research programs.

    oai_token-act-pair · 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
    SBATCH
    -0.75
     EconPapers
    -0.73
    {}{}
    -0.69
     doInBackground
    -0.69
    WebVitals
    -0.69
    OGND
    -0.69
    "}")
    -0.67
    protoc
    -0.66
     ins
    -0.63
     lateinit
    -0.63
    POSITIVE LOGITS
     at
    0.59
     no
    0.52
     or
    0.46
     محفوظة
    0.45
     a
    0.44
    ιβ
    0.43
     let
    0.42
     by
    0.41
     from
    0.41
     some
    0.41
    Activations Density 3.086%

    No Known Activations