© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8002
    Prev
    Next
    INDEX
    Explanations

    defining technical terms

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming or data structures

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

    Defining terms

    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
     term
    -1.52
     terms
    -1.43
    term
    -1.30
    terms
    -1.29
    Terms
    -1.27
    Term
    -1.25
     Terms
    -1.20
     Term
    -1.17
     TERM
    -1.15
     termes
    -1.13
    POSITIVE LOGITS
    bootstrapcdn
    0.89
    GTCX
    0.79
    FunctionFlags
    0.73
    InputBorder
    0.71
     wireType
    0.70
     dAtA
    0.68
    +#+
    0.67
    printStackTrace
    0.67
    ništvo
    0.66
    closedir
    0.66
    Activations Density 4.666%

    No Known Activations