© 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. 10457
    Prev
    Next
    INDEX
    Explanations

    terms and acronyms related to protein analysis and chromatography, especially SDS-PAGE,.

    oai_token-act-pair · gemini-2.0-flash

    Scientific lab procedures

    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
     مشين
    -0.90
    Personendaten
    -0.84
     SafeMath
    -0.80
     AttributeSet
    -0.79
    RenderAtEndOf
    -0.76
    NameInMap
    -0.75
    PreferredItem
    -0.74
    InputBorder
    -0.71
     StatefulWidget
    -0.71
    ConstraintMaker
    -0.71
    POSITIVE LOGITS
     anteriore
    0.45
    Autoritní
    0.43
     beds
    0.42
     scattata
    0.40
    wal
    0.40
     μή
    0.38
     regi
    0.37
     شیمی
    0.37
    wag
    0.36
     avantages
    0.35
    Activations Density 3.011%

    No Known Activations