© 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. 4926
    Prev
    Next
    INDEX
    Explanations

    words that are often connecting words or verbs, and other words surrounding them

    oai_token-act-pair · 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
     rather
    -0.83
    ReusableCell
    -0.75
    rather
    -0.75
     kasarigan
    -0.73
    ScopeManager
    -0.71
    Rather
    -0.71
     Rather
    -0.71
    InputBorder
    -0.69
     AssemblyCulture
    -0.67
    interopRequire
    -0.65
    POSITIVE LOGITS
    béco
    0.49
    hiel
    0.48
    ***/
    0.45
    ༻
    0.45
    ânsito
    0.44
    MERC
    0.44
    RPD
    0.44
    țional
    0.43
    irited
    0.43
    lecular
    0.42
    Activations Density 9.253%

    No Known Activations