© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    words related to teaching English as a second language, and German verbs

    oai_token-act-pair · gemini-2.0-flash

    academic/language/learning

    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
    ãng
    -0.53
    ImageContext
    -0.52
     /\.
    -0.51
    XtraGrid
    -0.49
    VIAF
    -0.47
    ώ
    -0.46
     Viber
    -0.44
     girdle
    -0.43
     '\\;'
    -0.43
    Qt
    -0.43
    POSITIVE LOGITS
     Larsson
    0.55
     Factbook
    0.54
    Биография
    0.54
     consultato
    0.54
    stateProvider
    0.52
    MessageTagHelper
    0.52
    lilla
    0.52
    laca
    0.51
     flashing
    0.50
    StoryboardSegue
    0.50
    Activations Density 8.942%

    No Known Activations