© 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. 4250
    Prev
    Next
    INDEX
    Explanations

    words related to art exhibitions

    oai_token-act-pair · gemini-2.0-flash

    terms related to art and exhibitions

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

    art

    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
    ThroughAttribute
    -0.82
    IntoConstraints
    -0.72
     autorytatywna
    -0.72
    awaiter
    -0.68
     ujednoznacz
    -0.66
    KommentareTeilen
    -0.66
    Enllaces
    -0.64
    WriteAttribute
    -0.64
     للاسماء
    -0.63
    <?
    -0.63
    POSITIVE LOGITS
    ukkah
    0.43
     representations
    0.42
    installa
    0.41
     depicting
    0.39
     Cato
    0.38
     inoxidable
    0.38
     SetUp
    0.38
     popolare
    0.37
     representation
    0.37
     Darstellung
    0.37
    Activations Density 4.157%

    No Known Activations