© 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. 10522
    Prev
    Next
    INDEX
    Explanations

    mentions of alpha-actin and angiotensin II in the context of muscle cell transcription

    oai_token-act-pair · gemini-2.0-flash

    terms related to smooth muscle actin

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

    blood vessel, muscle

    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
     >=",
    -0.68
    DoubleQuotes
    -0.63
    AnchorStyles
    -0.63
    eror
    -0.54
     Wern
    -0.52
    είο
    -0.51
    angering
    -0.51
    ionalmente
    -0.49
    AddHtmlAttribute
    -0.49
     compter
    -0.49
    POSITIVE LOGITS
    EndGlobalSection
    0.63
    principalColumn
    0.59
    omla
    0.54
     smooth
    0.54
    Personensuche
    0.51
    PRWEB
    0.50
    ngdoc
    0.49
    ]--;
    0.47
     Smooth
    0.46
    smooth
    0.46
    Activations Density 2.053%

    No Known Activations