© 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. 12723
    Prev
    Next
    INDEX
    Explanations

    text about political elections.

    oai_token-act-pair · gemini-2.0-flash

    concepts of closeness

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

    close

    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
    uary
    -0.57
     pulumi
    -0.57
     amarillas
    -0.56
    twimg
    -0.55
    yntaxException
    -0.53
    actylus
    -0.51
    bukkit
    -0.51
    unmodifiable
    -0.49
    orcid
    -0.49
     Gespräch
    -0.49
    POSITIVE LOGITS
     close
    1.48
     Close
    1.23
     CLOSE
    1.15
    Close
    1.14
    close
    1.12
     closest
    1.09
     tight
    1.06
     closer
    1.00
     closely
    0.93
     closeness
    0.93
    Activations Density 1.329%

    No Known Activations