© 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. 3478
    Prev
    Next
    INDEX
    Explanations

    words ending in "ic", "ed", "y", "b", "f", "h", "l"

    oai_token-act-pair · gemini-2.0-flash

    technical terms or 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
     Winaray
    -0.74
    RTEX
    -0.66
     tartalomajánló
    -0.64
    amerikanische
    -0.61
    declarations
    -0.57
    CrossRef
    -0.54
     समीक्षक
    -0.53
    IANGLES
    -0.51
    ewoo
    -0.51
     getItemCount
    -0.51
    POSITIVE LOGITS
    ENDIAN
    0.54
     переписи
    0.50
     onPage
    0.49
     analisi
    0.48
    ruptcy
    0.47
     ziua
    0.47
     sbag
    0.47
    vud
    0.47
     Mär
    0.47
    Josef
    0.47
    Activations Density 2.797%

    No Known Activations