© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3851
    Prev
    Next
    INDEX
    Explanations

    mentions of conflict, hunting and violence

    oai_token-act-pair · gemini-2.0-flash

    Negative themes and violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IntoConstraints
    -0.53
    országban
    -0.50
     permeability
    -0.45
    ||}
    -0.45
     laik
    -0.45
     $('<
    -0.44
    unsplash
    -0.44
     Wys
    -0.43
     Inoc
    -0.43
     ajan
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.56
    principalColumn
    0.56
    utives
    0.53
    حياته
    0.52
    addPreferredGap
    0.52
    errit
    0.52
    Спасылкі
    0.51
    prus
    0.50
     mis
    0.50
     Процитовано
    0.48
    Activations Density 2.772%

    No Known Activations