© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14012
    Prev
    Next
    INDEX
    Explanations

    verbs related to acting or gesturing as well as references to guns or sexual acts/body parts

    oai_token-act-pair · gemini-2.0-flash

    Adult themes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     AssemblyCulture
    -0.79
     <<<<<<<<<<<<<<
    -0.66
    клопе
    -0.62
     المعيارى
    -0.61
    NavController
    -0.60
    /**
    -0.60
     propOrder
    -0.59
    uesia
    -0.57
    AddTagHelper
    -0.56
    UnknownFieldSet
    -0.56
    POSITIVE LOGITS
     acrylique
    0.54
     poussière
    0.50
    anthrene
    0.49
    férences
    0.48
     palmas
    0.47
    hade
    0.46
    acakt
    0.45
     caoutchouc
    0.45
     ready
    0.45
     canadien
    0.45
    Activations Density 1.560%

    No Known Activations