© 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. 1873
    Prev
    Next
    INDEX
    Explanations

    speech verbs like "tell", "say", "ask", or "know", sometimes including "you" or "them"

    oai_token-act-pair · gemini-2.0-flash

    tell

    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
    rungsseite
    -0.94
    \{\\
    -0.78
    
    -0.74
     الحره
    -0.71
     utafitiHapana
    -0.67
     مرئيه
    -0.66
    WithIOException
    -0.63
    ANGES
    -0.61
     initComponents
    -0.60
    Clik
    -0.60
    POSITIVE LOGITS
     me
    0.52
    хьтан
    0.52
     us
    0.49
     you
    0.45
     CreateTagHelper
    0.45
     jadx
    0.41
    polyline
    0.41
    katan
    0.40
     vej
    0.40
     diferenci
    0.39
    Activations Density 5.129%

    No Known Activations