© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11312
    Prev
    Next
    INDEX
    Explanations

    the prefix "ste" and the word "pole," and words similar to "pole"

    oai_token-act-pair · gemini-2.0-flash

    ste

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Ste
    -1.85
     ste
    -1.80
    Ste
    -1.79
    ste
    -1.73
     STE
    -1.30
    STE
    -1.10
     Steward
    -0.84
     steaming
    -0.82
     steam
    -0.79
     Steep
    -0.79
    POSITIVE LOGITS
    SBATCH
    0.72
     noDo
    0.59
    Rujuakan
    0.58
     snippetHide
    0.55
     Мексичка
    0.54
    AnimationsModule
    0.52
    etje
    0.49
    SEGUIR
    0.49
     kasarigan
    0.48
    KURZBESCHREIBUNG
    0.47
    Activations Density 3.615%

    No Known Activations