© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2043
    Prev
    Next
    INDEX
    Explanations

    information related to a person's education, including degrees, universities, and honors

    oai_token-act-pair · gemini-2.0-flash

    words related to education and academic achievements

    np_token-act-pair-logits · gpt-4o-mini

    academic degrees

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    دانشنامهٔ
    -0.84
    Autoritní
    -0.82
    fjspx
    -0.79
     HasFactory
    -0.73
     estimés
    -0.69
     дописавши
    -0.68
    
    -0.68
    ModelSerializer
    -0.67
    Portale
    -0.66
     ostavi
    -0.66
    POSITIVE LOGITS
     in
    0.45
     concentrating
    0.44
     sasaran
    0.43
     focusing
    0.42
     Centrale
    0.42
     Focusing
    0.41
    centra
    0.41
     centers
    0.41
    enumi
    0.41
     étudier
    0.40
    Activations Density 3.426%

    No Known Activations