© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12598
    Prev
    Next
    INDEX
    Explanations

    fragments of sentences containing the word "would"

    oai_token-act-pair · gemini-2.0-flash

    leave

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ValueStyle
    -0.82
    enumii
    -0.75
    tanleria
    -0.70
    tagext
    -0.68
    ftagPool
    -0.66
    IndentedString
    -0.65
    WebVitals
    -0.61
     viewType
    -0.58
     MenuView
    -0.58
    PullParser
    -0.57
    POSITIVE LOGITS
     leaves
    0.79
    leaves
    0.70
     leave
    0.68
     Leaves
    0.64
     let
    0.63
     leaving
    0.62
    leave
    0.59
     Leaving
    0.59
     Leave
    0.57
    leaving
    0.55
    Activations Density 3.344%

    No Known Activations