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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16291
    Prev
    Next
    INDEX
    Explanations

    negations and possibly also references to legal and social issues, including personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    wish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Мексичка
    -0.55
     dAtA
    -0.54
    EDEFAULT
    -0.51
    IUrlHelper
    -0.49
    paddingVertical
    -0.47
    mapsto
    -0.45
    optarg
    -0.45
     Chwiliwch
    -0.44
    NameInMap
    -0.43
     Vereinigte
    -0.42
    POSITIVE LOGITS
     wish
    2.89
     wishes
    2.47
     wished
    2.45
    wish
    2.42
     Wish
    2.38
    Wish
    2.23
     WISH
    2.20
     wishing
    2.19
     Wishes
    1.94
     Wishing
    1.64
    Activations Density 9.784%

    No Known Activations