© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8434
    Prev
    Next
    INDEX
    Explanations

    references to Google and search queries

    oai_token-act-pair · gemini-2.0-flash

    Google

    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
     Google
    -2.98
    Google
    -2.80
     google
    -2.64
     GOOGLE
    -2.36
    google
    -2.34
    GOOGLE
    -2.14
    谷歌
    -1.65
    goog
    -1.41
     googled
    -1.34
    googleapis
    -1.24
    POSITIVE LOGITS
    nonatomic
    0.59
    '][]
    0.58
     noqa
    0.54
    WriteLiteral
    0.51
    +#+#
    0.49
     gawas
    0.49
     invokingState
    0.47
    LayoutInflater
    0.47
     Barbosa
    0.46
    WriteTagHelper
    0.46
    Activations Density 1.924%

    No Known Activations