© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4654
    Prev
    Next
    INDEX
    Explanations

    the word "armed", and possibly words associated with crime

    oai_token-act-pair · gemini-2.0-flash

    armed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    IVEREF
    -1.23
     pinulongan
    -1.20
    脚注の使い方
    -1.15
     ExecuteAsync
    -1.15
     NSCoder
    -1.09
     estekak
    -1.04
     unknownFields
    -1.02
     kasarigan
    -1.02
    WriteTagHelper
    -1.01
    Tikang
    -0.99
    POSITIVE LOGITS
     
    0.87
     the
    0.69
     can
    0.63
     is
    0.61
     still
    0.59
     of
    0.58
     volume
    0.57
    ’
    0.56
     are
    0.56
     in
    0.55
    Activations Density 1.347%

    No Known Activations