© 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. 420
    Prev
    Next
    INDEX
    Explanations

    the word "m" or words followed by in' or words related to feelings, tiredness, or internal struggle

    oai_token-act-pair · gemini-2.0-flash

    lyrics

    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
    RegistryLite
    -0.43
    TagHelpers
    -0.43
    </thead>
    -0.42
    #![
    -0.40
    BagConstraints
    -0.40
     Esta
    -0.38
    then
    -0.38
    Становништво
    -0.38
    AccessorTable
    -0.38
    XmlAccessType
    -0.37
    POSITIVE LOGITS
    expandindo
    0.99
    Drilling
    0.65
    rungsseite
    0.64
     Wiktionnaire
    0.63
    Cloning
    0.60
    Cleaning
    0.59
    Pinned
    0.58
    Inserting
    0.57
    rhosis
    0.57
    alyptus
    0.57
    Activations Density 2.152%

    No Known Activations