© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9910
    Prev
    Next
    INDEX
    Explanations

    past tense forms of 'is', and some words occurring when describing sports

    oai_token-act-pair · gemini-2.0-flash

    was/were

    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
    __(/*!
    -0.64
    
    -0.59
    脚注の使い方
    -0.58
    multicolumn
    -0.54
    StoryboardSegue
    -0.54
    DotNetBar
    -0.53
    Rgds
    -0.52
    AxisAlignment
    -0.52
    曖昧さ回避
    -0.51
    fromnode
    -0.50
    POSITIVE LOGITS
     himo
    0.57
     HED
    0.48
    Rüyada
    0.48
     TextAlign
    0.47
    romyalgia
    0.47
    EReference
    0.46
     MOQ
    0.46
     ellipsoid
    0.46
    äft
    0.45
    uración
    0.45
    Activations Density 1.379%

    No Known Activations