© 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. 12670
    Prev
    Next
    INDEX
    Explanations

    references to patents and applications for patents

    oai_token-act-pair · gemini-2.0-flash

    capitalized words or phrases

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

    period

    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
     Efq
    -0.91
     Савезне
    -0.91
     protoimpl
    -0.82
     oprot
    -0.82
    存于互联网档案馆
    -0.82
    tagHelperRunner
    -0.81
     ſche
    -0.81
     AttributeSet
    -0.81
     Мексичка
    -0.80
    InitVars
    -0.80
    POSITIVE LOGITS
     A
    0.47
     W
    0.42
     t
    0.42
     The
    0.42
     N
    0.40
     to
    0.40
     w
    0.39
     acción
    0.38
    ,
    0.38
    ыл
    0.38
    Activations Density 2.087%

    No Known Activations