© 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. 13562
    Prev
    Next
    INDEX
    Explanations

    words that often appear in scientific/research papers, technical manuals, tutorial instructions, or code documentation

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    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
     Majefty
    -1.30
     pleaſure
    -1.24
     Reſ
    -1.21
     purpoſe
    -1.20
     houſe
    -1.19
     photolibrary
    -1.19
     Efq
    -1.18
     ſeveral
    -1.16
     itſelf
    -1.16
     ſtate
    -1.16
    POSITIVE LOGITS
     demás
    0.36
     próprios
    0.35
     dessus
    0.32
     atas
    0.32
    .
    0.28
     to
    0.28
     millón
    0.28
     in
    0.28
    ,
    0.27
    :
    0.26
    Activations Density 36.181%

    No Known Activations