© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11628
    Prev
    Next
    INDEX
    Explanations

    titles and organizations affiliated with higher education

    oai_token-act-pair · gemini-2.0-flash

    professor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     professores
    -0.54
     Krakowie
    -0.51
    $_['
    -0.51
     teacher
    -0.50
    CJK
    -0.49
     dė
    -0.48
     faculty
    -0.48
     Profesor
    -0.47
     rentrée
    -0.47
    andExpect
    -0.47
    POSITIVE LOGITS
    клопе
    0.68
    Sklici
    0.66
    bigsqcup
    0.65
    execSQL
    0.64
    AnimationsModule
    0.63
    AutoScaleMode
    0.63
     Roskov
    0.62
    UGU
    0.59
     beginnetje
    0.57
    namentales
    0.57
    Activations Density 6.295%

    No Known Activations