© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5111
    Prev
    Next
    INDEX
    Explanations

    words related to cultural values and traditions

    oai_token-act-pair · gemini-2.0-flash

    ity

    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
    IVEREF
    -0.62
    DispatchToProps
    -0.60
     переписи
    -0.59
    romeda
    -0.56
    StoryboardSegue
    -0.53
     downvoted
    -0.53
     nonatomic
    -0.52
    CodedInputStream
    -0.52
     فريبيس
    -0.51
    PMailer
    -0.51
    POSITIVE LOGITS
     which
    0.81
     that
    0.69
     whose
    0.67
     who
    0.66
    <bos>
    0.64
     what
    0.60
    UVWXYZ
    0.56
     duquel
    0.54
     kív
    0.54
     waarop
    0.53
    Activations Density 1.555%

    No Known Activations