© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10139
    Prev
    Next
    INDEX
    Explanations

    instances of starting a race

    oai_token-act-pair · gemini-2.0-flash

    drawing-related terms and concepts

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    oa̍t
    -0.61
     betweenstory
    -0.58
    EndInit
    -0.57
    Carcinogenicity
    -0.55
    ьаж
    -0.52
     bodyParser
    -0.52
     SwitchCompat
    -0.52
    
    -0.51
    AxisAlignment
    -0.50
    IGraphics
    -0.49
    POSITIVE LOGITS
    drawing
    0.54
     draw
    0.53
    ropia
    0.52
     drawing
    0.51
     HasFactory
    0.50
     Draws
    0.49
     tartalomajánló
    0.49
    LookAnd
    0.49
     enfance
    0.48
     linkovi
    0.48
    Activations Density 0.362%

    No Known Activations