© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2179
    Prev
    Next
    INDEX
    Explanations

    a variety of emotional and descriptive words

    oai_token-act-pair · gemini-2.0-flash

    quite

    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
    CrossRef
    -0.52
    StoreMessageInfo
    -0.47
     onBackPressed
    -0.47
    CustomAttributes
    -0.46
    ⓧ
    -0.46
    respectively
    -0.45
    agot
    -0.45
    AndEndTag
    -0.44
    Specifically
    -0.44
     soigne
    -0.44
    POSITIVE LOGITS
     quite
    3.20
    quite
    2.95
     Quite
    2.94
    Quite
    2.89
     uite
    1.60
     ganske
    1.26
     ganska
    1.01
     bastante
    0.99
     destul
    0.90
    けっこう
    0.88
    Activations Density 7.952%

    No Known Activations