© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8747
    Prev
    Next
    INDEX
    Explanations

    the word "able", sometimes also finding "failing" or "dismiss"

    oai_token-act-pair · gemini-2.0-flash

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     able
    -2.03
     Able
    -1.39
    Able
    -1.30
     capaz
    -1.11
    <bos>
    -1.10
     unable
    -1.09
     capaces
    -1.05
     capables
    -0.97
    able
    -0.97
     capable
    -0.97
    POSITIVE LOGITS
    hdashline
    0.61
    AutoresizingMask
    0.59
    moveToFirst
    0.59
    InSection
    0.56
    :].
    0.56
    TProtocol
    0.55
     BoxFit
    0.54
    存于互联网档案馆
    0.53
    CppMethod
    0.52
     Wiktionnaire
    0.52
    Activations Density 1.474%

    No Known Activations