© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 603
    Prev
    Next
    INDEX
    Explanations

    terms related to physical processes, especially in technical documents

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific 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
     propOrder
    -0.50
    webElementGuid
    -0.49
    èlement
    -0.46
    cabulary
    -0.46
    ngths
    -0.46
    ۇ
    -0.45
    ations
    -0.45
    SuppressLint
    -0.45
    település
    -0.44
    ngilizce
    -0.44
    POSITIVE LOGITS
    ChildScrollView
    0.75
     stores
    0.68
     places
    0.65
     OMIT
    0.62
     projects
    0.61
    BeginContext
    0.60
    RefNanny
    0.60
    ArgsConstructor
    0.59
    WithFormat
    0.58
     abstracts
    0.58
    Activations Density 8.472%

    No Known Activations