© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10916
    Prev
    Next
    INDEX
    Explanations

    second or third person pronouns, and words about football teams or business offers

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     myſelf
    -0.87
     pleaſure
    -0.84
     ſtand
    -0.83
    ſelf
    -0.82
     ſmall
    -0.81
     himſelf
    -0.79
     purpoſe
    -0.79
     cauſe
    -0.79
     diſt
    -0.78
    ſelves
    -0.77
    POSITIVE LOGITS
     tra
    0.48
     risco
    0.46
     rayos
    0.44
     tr
    0.43
    過的
    0.42
    endregion
    0.41
     l
    0.41
     sûr
    0.40
     Tr
    0.40
    ree
    0.40
    Activations Density 1.158%

    No Known Activations