© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6260
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to a queen with some modal verbs

    oai_token-act-pair · gemini-2.0-flash

    resisting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    kháu
    -0.84
     Theſe
    -0.73
     initComponents
    -0.73
     Efq
    -0.71
    mybatisplus
    -0.68
    MigrationBuilder
    -0.67
     myſelf
    -0.67
     gynhyrchwyd
    -0.66
    /*
    -0.65
    awtextra
    -0.65
    POSITIVE LOGITS
     restraint
    0.75
     restrain
    0.73
     Restra
    0.68
     stifle
    0.68
     restrained
    0.64
     suppress
    0.64
     resisting
    0.60
     restraining
    0.59
     resisted
    0.58
     suppressing
    0.57
    Activations Density 0.954%

    No Known Activations