© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    acronyms for organizations

    oai_token-act-pair · gemini-2.0-flash

    abbreviations or acronyms

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

    acronyms Method used: 3 — detects uppercase acronyms/abbreviations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    <bos>
    -0.51
     R
    -0.49
     Zus
    -0.48
     Band
    -0.47
     Z
    -0.47
    FLICT
    -0.46
     scouts
    -0.46
     stent
    -0.45
     r
    -0.45
     valence
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.86
    DockStyle
    0.81
     EconPapers
    0.75
     الحره
    0.72
    CompleteListener
    0.71
     surla
    0.71
     OnTrigger
    0.67
    ValueStyle
    0.66
     becauſe
    0.66
     MainAxisSize
    0.66
    Activations Density 0.790%

    No Known Activations