© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12256
    Prev
    Next
    INDEX
    Explanations

    the name "Sheryl" or "Sher".

    oai_token-act-pair · gemini-2.0-flash

    Sher

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    τεύ
    -0.53
    TabStop
    -0.51
    hape
    -0.50
     clima
    -0.49
     ['$
    -0.48
     aleg
    -0.48
     پاس
    -0.47
     bis
    -0.45
    TypedDataSet
    -0.45
     adjusted
    -0.45
    POSITIVE LOGITS
    :✨
    0.66
    Przypisy
    0.64
    RegressionTest
    0.59
    tagext
    0.58
    EndProject
    0.58
    NUMX
    0.56
     gynhyrchwyd
    0.54
    yorsunuz
    0.53
    ViewFeatures
    0.53
     يتيمه
    0.53
    Activations Density 0.164%

    No Known Activations