© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14339
    Prev
    Next
    INDEX
    Explanations

    modal verbs, especially "can"

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     canst
    -0.72
     riesce
    -0.60
     pouvez
    -0.60
    évaluateur
    -0.56
    Can
    -0.55
     للمعارف
    -0.54
     能
    -0.53
    又能
    -0.53
    وانید
    -0.53
    can
    -0.53
    POSITIVE LOGITS
    Lähteet
    0.75
    Geplaatst
    0.60
    CONSIDER
    0.59
     intentional
    0.57
    ïsme
    0.56
    خذ
    0.54
    msgSender
    0.54
     preferring
    0.52
    haviour
    0.51
    thday
    0.50
    Activations Density 9.625%

    No Known Activations