© 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. 8668
    Prev
    Next
    INDEX
    Explanations

    the prefix "une" coupled and "IE" to a lesser extent

    oai_token-act-pair · gemini-2.0-flash

    une

    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
    protoimpl
    -0.77
     noires
    -0.69
    encodeWith
    -0.67
    windowFixed
    -0.62
     kasarigan
    -0.61
    Personensuche
    -0.60
     '\\;'
    -0.60
     initComponents
    -0.59
    ագրություններ
    -0.59
    rungsseite
    -0.59
    POSITIVE LOGITS
    qual
    0.47
    vor
    0.43
    lem
    0.43
    tagHelperRunner
    0.42
    ReusableCell
    0.42
    mite
    0.40
    latform
    0.40
    con
    0.40
     mapStateToProps
    0.40
     qualify
    0.40
    Activations Density 5.762%

    No Known Activations