© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15319
    Prev
    Next
    INDEX
    Explanations

    the full phrase "at the right time, at the right place, for the right reason"

    oai_token-act-pair · gemini-2.0-flash

    right

    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
    skjaer
    -0.67
    middels
    -0.61
    ViewFeatures
    -0.60
    Zeneca
    -0.59
     createSlice
    -0.59
    AccessorTable
    -0.56
    Obrázky
    -0.56
    transQ
    -0.55
     pomocou
    -0.54
    calientes
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    AnimationsModule
    0.55
     @"/
    0.54
     forever
    0.52
    InjectAttribute
    0.50
     invokingState
    0.50
    forever
    0.48
    oun
    0.48
     McKe
    0.48
     ín
    0.46
    Activations Density 0.446%

    No Known Activations