© 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. 13423
    Prev
    Next
    INDEX
    Explanations

    references to Minnesota, hockey, and universities.

    oai_token-act-pair · gemini-2.0-flash

    location names

    np_max-act-logits · 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
    таратура
    -0.66
     bParam
    -0.62
    tvguidetime
    -0.61
    inin
    -0.59
    SequentialGroup
    -0.58
    addCriterion
    -0.58
    SpringBootTest
    -0.57
     Mineral
    -0.57
     vPvB
    -0.56
    udur
    -0.56
    POSITIVE LOGITS
    tagHelperRunner
    0.69
    sidemargin
    0.61
    __*/
    0.49
    YI
    0.46
     lakes
    0.46
     Lakes
    0.45
     withal
    0.44
     jadx
    0.44
    yi
    0.43
    articulo
    0.43
    Activations Density 2.590%

    No Known Activations