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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4486
    Prev
    Next
    INDEX
    Explanations

    words that have the suffixes "ed", "ing", "tion", "ers", "cian", "ly", "ful", "less", "able", "ive".

    oai_token-act-pair · gemini-2.0-flash

    Words ending in "ing""ed"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    BM
    -0.53
    Lähteet
    -0.47
    发表于
    -0.47
    یب
    -0.47
     BM
    -0.46
     beverly
    -0.46
     PX
    -0.46
    entee
    -0.46
    RTEE
    -0.46
    eseorang
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.81
    UnsafeEnabled
    0.74
     NSCoder
    0.70
    AnchorStyles
    0.60
    protoimpl
    0.56
     ویکی‌پدیا
    0.56
    DockStyle
    0.55
    ++;
    0.55
    SourceChecksum
    0.54
    MemoryWarning
    0.52
    Activations Density 3.127%

    No Known Activations