© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3189
    Prev
    Next
    INDEX
    Explanations

    words indicating strong opinions or emotional reactions to creative works and people

    oai_token-act-pair · gemini-2.0-flash

    words related to achievement or success

    np_token-act-pair-logits · gpt-4o-mini
    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
    !*\
    -0.64
    saraba
    -0.52
    پیوند
    -0.43
     perten
    -0.42
    dataclass
    -0.42
     Farmhouse
    -0.42
     naran
    -0.41
     gelin
    -0.41
     espacial
    -0.41
     correg
    -0.41
    POSITIVE LOGITS
     stole
    0.97
     steals
    0.75
     steal
    0.75
    encodeWith
    0.73
     InputDecoration
    0.72
     charmed
    0.72
     stealing
    0.71
     win
    0.71
     gain
    0.70
    sizeCache
    0.69
    Activations Density 1.577%

    No Known Activations