© 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. 3151
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to doing well, or receiving assistance

    oai_token-act-pair · gemini-2.0-flash

    "from" in different languages

    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
     EconPapers
    -0.81
    expandindo
    -0.68
     Form
    -0.66
    FORM
    -0.66
    ToRefresh
    -0.65
    Form
    -0.63
    Fra
    -0.61
    forme
    -0.59
    tagHelperRunner
    -0.57
    liceerd
    -0.56
    POSITIVE LOGITS
     from
    2.38
     dari
    1.24
    จาก
    1.23
    from
    1.13
     từ
    1.10
     partir
    1.05
     desde
    1.05
     från
    1.02
    从
    1.00
     از
    0.96
    Activations Density 1.069%

    No Known Activations