© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11266
    Prev
    Next
    INDEX
    Explanations

    positive or complimentary attributes of people or organizations

    oai_token-act-pair · gemini-2.0-flash

    related to careers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Económica
    -0.75
    )";
    -0.71
    ImageContext
    -0.64
    principalColumn
    -0.63
     heilig
    -0.63
     Efq
    -0.62
     للاسماء
    -0.62
     garnet
    -0.61
    #+#
    -0.61
     Superhost
    -0.60
    POSITIVE LOGITS
    netinet
    0.52
    rī
    0.47
     Administrativna
    0.46
     saites
    0.45
     ex
    0.45
     run
    0.45
     My
    0.44
    '][]
    0.44
     radi
    0.43
    aibo
    0.43
    Activations Density 5.115%

    No Known Activations