© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15173
    Prev
    Next
    INDEX
    Explanations

    descriptions of weapon possession or retrieval

    oai_token-act-pair · gemini-2.0-flash

    weapons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    -0.71
     Theſe
    -0.66
     themſelves
    -0.62
     iconFacebook
    -0.60
     Monfieur
    -0.59
     صوتيه
    -0.57
     ſtill
    -0.55
    tagext
    -0.54
     mijne
    -0.54
    InlineData
    -0.54
    POSITIVE LOGITS
    webElement
    0.69
     مشين
    0.59
     ddelweddau
    0.58
     Bose
    0.57
    География
    0.56
     tiguan
    0.53
    μαν
    0.50
    ████
    0.50
    在地
    0.50
    TagMode
    0.48
    Activations Density 1.280%

    No Known Activations