© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13703
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to activate on a wide variety of words with no clear pattern

    oai_token-act-pair · gemini-2.0-flash

    Relationships/family

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    principalColumn
    -0.79
    éndole
    -0.62
     MainAxisSize
    -0.60
     contactez
    -0.59
    Források
    -0.58
    yntaxException
    -0.57
    Spoljašnje
    -0.57
    Vidite
    -0.57
    dumps
    -0.57
     Sites
    -0.56
    POSITIVE LOGITS
    Mothers
    0.54
     OMIT
    0.49
     couples
    0.48
     relationships
    0.47
    صه
    0.47
     tables
    0.47
    merie
    0.46
    Relations
    0.45
     fathers
    0.45
    TintMode
    0.45
    Activations Density 5.689%

    No Known Activations