© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8501
    Prev
    Next
    INDEX
    Explanations

    the trigram "sha" and/or names containing them

    oai_token-act-pair · gemini-2.0-flash

    Sha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Sha
    -2.70
    Sha
    -2.64
     sha
    -2.45
    sha
    -2.30
     SHA
    -1.73
    SHA
    -1.53
     Shak
    -1.35
     shaking
    -1.28
     shaker
    -1.24
     Shaker
    -1.22
    POSITIVE LOGITS
     esternos
    0.59
     hilar
    0.59
     >=",
    0.57
    testens
    0.56
     propOrder
    0.56
     Divinity
    0.55
     Wrapping
    0.54
     intersti
    0.53
     MaterialApp
    0.52
    beur
    0.52
    Activations Density 0.519%

    No Known Activations