© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 11622
    Prev
    Next
    INDEX
    Explanations

    the words "deserve," "chiefs," and "warrant," as well as other legal and military jargon.

    oai_token-act-pair · gemini-2.0-flash

    deserve

    np_max-act · gemini-2.0-flash

    deserve

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109

    deserve

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     deserve
    -0.79
    its
    -0.74
     deserves
    -0.73
    SOUNDBITE
    -0.68
     deserved
    -0.61
    ITS
    -0.59
    BC
    -0.57
    liflower
    -0.52
    âce
    -0.51
     benne
    -0.50
    POSITIVE LOGITS
    apunov
    0.64
    __))
    0.56
    }^{+}\
    0.56
    ViewImports
    0.56
    AnchorTagHelper
    0.55
    RegistryLite
    0.52
    arXiv
    0.52
    xtext
    0.51
    ^{+}\
    0.51
    >");
    
    0.51
    Activations Density 4.807%

    No Known Activations