© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13194
    Prev
    Next
    INDEX
    Explanations

    recipe ingredients, instructions, and related interjections

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     esistono
    -0.40
    ="@+
    -0.40
    Legături
    -0.40
     لاس
    -0.39
    tame
    -0.38
    nadores
    -0.38
     hàng
    -0.37
     debout
    -0.36
     bordados
    -0.36
    ParallelGroup
    -0.36
    POSITIVE LOGITS
     ویکی‌پدیا
    0.84
    MessageTagHelper
    0.66
    httphttps
    0.65
    jooq
    0.61
    Попис
    0.59
     المعيارى
    0.58
    scrapy
    0.57
     texinfo
    0.57
     Vikipedi
    0.57
    aarrggbb
    0.56
    Activations Density 8.038%

    No Known Activations