© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4658
    Prev
    Next
    INDEX
    Explanations

    conjunction words, especially "so" and "and", and a few related words like "but", "to", "if" and commas

    oai_token-act-pair · gemini-2.0-flash

    separating phrases

    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
    Don
    -1.18
     Don
    -1.15
    Make
    -1.12
    Try
    -1.07
     Try
    -1.06
     Make
    -1.06
     Keep
    -1.05
    Be
    -1.05
     Be
    -1.02
    Keep
    -1.02
    POSITIVE LOGITS
    expandindo
    0.68
    brainly
    0.64
    ]--;
    0.63
    aturing
    0.57
    Ecotoxicity
    0.56
    最快更新
    0.52
     numerus
    0.52
    stdc
    0.51
    UNITY
    0.50
    PRNewswire
    0.49
    Activations Density 5.350%

    No Known Activations