© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6808
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating an issue or controversy, along with associated terms.

    oai_token-act-pair · gemini-2.0-flash

    negative situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -1.03
     itſelf
    -0.97
     Theſe
    -0.91
     Efq
    -0.89
     Jefus
    -0.89
     Monfieur
    -0.87
     Chriftian
    -0.86
     himſelf
    -0.85
     poffe
    -0.82
     Anſ
    -0.82
    POSITIVE LOGITS
     i
    0.55
     by
    0.54
     G
    0.50
     over
    0.50
     hö
    0.50
     with
    0.50
     p
    0.50
     within
    0.49
    .
    0.49
     die
    0.48
    Activations Density 5.480%

    No Known Activations