© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7084
    Prev
    Next
    INDEX
    Explanations

    words related to the military and politics

    oai_token-act-pair · gemini-2.0-flash

    Military operations and personnel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     /\.
    -0.70
    存于互联网档案馆
    -0.60
    thâu
    -0.52
    boar
    -0.51
     /\.(
    -0.50
    脚注の使い方
    -0.50
    CodeAttribute
    -0.49
     driving
    -0.49
     conducción
    -0.49
     '-':
    -0.47
    POSITIVE LOGITS
     Roskov
    0.63
     poveznice
    0.61
    Normdaten
    0.54
    MENAFN
    0.54
     بيها
    0.53
    ----</
    0.53
     purpoſe
    0.52
     gynnwys
    0.52
    WebControls
    0.51
    yntaxException
    0.50
    Activations Density 4.184%

    No Known Activations