© 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. 3863
    Prev
    Next
    INDEX
    Explanations

    technical language about data analysis and classification methods

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax or keywords

    np_token-act-pair-logits · gpt-4o-mini

    data analysis and algorithms

    np_max-act-logits · gemini-2.0-flash
    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
    EndContext
    -0.61
    SourceChecksum
    -0.54
     للاسماء
    -0.54
     EventArgs
    -0.43
     dig
    -0.42
    лії
    -0.42
    ánh
    -0.42
    complexContent
    -0.42
    名詞
    -0.41
     태
    -0.41
    POSITIVE LOGITS
     useAuth
    0.63
     Infórmanos
    0.60
    ++
    0.58
     endwhile
    0.57
     自动
    0.57
    fowl
    0.55
    Lähteet
    0.55
     vrea
    0.55
    UserScript
    0.55
    InitVars
    0.53
    Activations Density 4.726%

    No Known Activations