© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12844
    Prev
    Next
    INDEX
    Explanations

    words associated with making suggestions, feeling unsure, or expressing ambiguity

    oai_token-act-pair · gemini-2.0-flash

    perhaps/maybe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Perhaps
    -0.73
     Maybe
    -0.69
    Perhaps
    -0.68
    Maybe
    -0.66
    maybe
    -0.65
    perhaps
    -0.62
     Probably
    -0.60
     maybe
    -0.57
     perhaps
    -0.56
     Possibly
    -0.52
    POSITIVE LOGITS
    ✨:
    0.90
     BoxFit
    0.78
    MockMvc
    0.71
     pleaſure
    0.70
    BagConstraints
    0.69
    SBATCH
    0.64
    /*
    0.64
    riwal
    0.64
    BASEPATH
    0.61
    UserScript
    0.61
    Activations Density 8.157%

    No Known Activations