© 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. 13000
    Prev
    Next
    INDEX
    Explanations

    words related to nanoscience and quantum physics

    oai_token-act-pair · gemini-2.0-flash

    academic/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_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
    -
    -0.23
    e
    -0.20
    y
    -0.20
    у
    -0.19
    ‌
    -0.18
    ↵
    -0.16
    is
    -0.16
    пи
    -0.16
    te
    -0.15
    _
    -0.14
    POSITIVE LOGITS
    principalColumn
    1.16
     Efq
    1.12
    mybatisplus
    1.12
     betweenstory
    1.10
     mergeFrom
    1.08
     protoimpl
    1.05
    +#+#
    1.04
    everywhere
    1.04
    HasAnnotation
    1.03
    Šalt
    1.00
    Activations Density 27.896%

    No Known Activations