© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3505
    Prev
    Next
    INDEX
    Explanations

    phrases related to step-by-step instructions, analytics, usability, and motherhood advice within online articles or tutorials

    oai_token-act-pair · gemini-2.0-flash

    make, makes, making

    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
     ease
    -0.94
     facilitate
    -0.84
    Ease
    -0.83
     facilitating
    -0.80
     Ease
    -0.79
     convenience
    -0.77
     удоб
    -0.71
     convenient
    -0.69
     Convenient
    -0.68
    ease
    -0.68
    POSITIVE LOGITS
     make
    1.29
     makes
    1.28
    Make
    1.23
     Make
    1.23
    make
    1.22
    makes
    1.16
     Makes
    1.15
    MAKE
    1.13
    Makes
    1.11
     making
    1.05
    Activations Density 2.791%

    No Known Activations