© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1894
    Prev
    Next
    INDEX
    Explanations

    imperative verbs like "take", "look", "make", and "keep".

    oai_token-act-pair · gemini-2.0-flash

    Imperative verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ']}
    -0.56
     Mar
    -0.55
    靡
    -0.55
    )):
    -0.55
     £
    -0.54
     ta
    -0.52
     EX
    -0.52
    rugada
    -0.50
     nakalista
    -0.50
    "))
    -0.50
    POSITIVE LOGITS
     myſelf
    0.91
     faſt
    0.79
     raiſ
    0.78
     uſed
    0.77
     reaſon
    0.77
     ſtate
    0.76
     thyself
    0.75
     purpoſe
    0.75
     ſeveral
    0.75
     pleaſure
    0.75
    Activations Density 1.695%

    No Known Activations