© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14337
    Prev
    Next
    INDEX
    Explanations

    words relating to crimes like extortion, blackmail, and abduction

    oai_token-act-pair · gemini-2.0-flash

    blackmail and extortion

    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
     embarazada
    -0.56
     Zusch
    -0.50
    исленность
    -0.50
     vicenda
    -0.49
     vertes
    -0.49
     barnen
    -0.49
     étanche
    -0.47
     fausse
    -0.47
     suivants
    -0.47
     fallecido
    -0.46
    POSITIVE LOGITS
    LabelTagHelper
    0.75
    ValueStyle
    0.73
     propOrder
    0.68
    AutoField
    0.66
     compel
    0.65
    RenderAtEndOf
    0.64
    IntoConstraints
    0.64
    +#+
    0.64
    AutoresizingMask
    0.63
    istoitu
    0.63
    Activations Density 1.433%

    No Known Activations