© 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. 12203
    Prev
    Next
    INDEX
    Explanations

    mentions of broadcasting and also seems to trigger on the pronoun "he"

    oai_token-act-pair · gemini-2.0-flash

    broadcast

    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
     myſelf
    -1.65
     Efq
    -1.57
     itſelf
    -1.52
     pleaſure
    -1.50
     Jefus
    -1.50
     Majefty
    -1.48
     Monfieur
    -1.45
     Diſ
    -1.42
     themſelves
    -1.42
     himſelf
    -1.41
    POSITIVE LOGITS
     
    0.68
     “
    0.64
     !=
    0.60
     Dahl
    0.59
     ==
    0.56
     Condens
    0.55
     Practitioners
    0.55
    Humble
    0.54
    sistors
    0.54
     raz
    0.54
    Activations Density 2.025%

    No Known Activations