© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2977
    Prev
    Next
    INDEX
    Explanations

    technical terms and scientific descriptions, particularly those related to chemistry, physics, and computer science

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical texts

    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
     abbildung
    -0.45
     tesettür
    -0.44
    Personendaten
    -0.43
     شیپور
    -0.40
     sprüche
    -0.40
     köpek
    -0.40
     bileklik
    -0.40
    Приятного
    -0.40
     gewel
    -0.39
     baskılı
    -0.39
    POSITIVE LOGITS
     tc
    0.39
    Przypisy
    0.37
     cs
    0.35
     ly
    0.35
     cal
    0.35
    coc
    0.35
     lc
    0.35
     gl
    0.35
    wcs
    0.34
    ต
    0.34
    Activations Density 21.303%

    No Known Activations