© 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. 13229
    Prev
    Next
    INDEX
    Explanations

    uses of "would", "could", and "should" style conditional sentences

    oai_token-act-pair · gemini-2.0-flash

    inside

    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
     ProtoMessage
    -0.52
    ništ
    -0.52
    рост
    -0.50
    XMLSchema
    -0.50
    Boyd
    -0.48
    ligheten
    -0.45
     Boyd
    -0.43
    förder
    -0.40
    illaries
    -0.40
    MemoryWarning
    -0.40
    POSITIVE LOGITS
     مشين
    0.63
    脚注の使い方
    0.63
     aspet
    0.61
     referenties
    0.59
    SceneManagement
    0.58
    TargetException
    0.57
    ⓧ
    0.54
    FirebaseDatabase
    0.53
     NLR
    0.53
     Constitución
    0.53
    Activations Density 1.618%

    No Known Activations