© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12117
    Prev
    Next
    INDEX
    Explanations

    tokens that are part of ordered lists or that often occur together as pairs, like "and" and a comma.

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Tikang
    -0.67
    Autoritní
    -0.61
     Réponses
    -0.60
    IBOutlet
    -0.60
     ICF
    -0.60
     Administrativna
    -0.58
     olympique
    -0.56
     Londra
    -0.56
     Wheaton
    -0.56
     Jérusalem
    -0.55
    POSITIVE LOGITS
     chi̍t
    0.47
    chluss
    0.47
     ""))
    0.46
     fieldNum
    0.45
    曖昧さ回避
    0.44
    ifflin
    0.43
    ToMany
    0.43
    NameInMap
    0.43
     \%}$
    0.43
     Group
    0.42
    Activations Density 3.659%

    No Known Activations