© 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. 13820
    Prev
    Next
    INDEX
    Explanations

    text related to primary and secondary education

    oai_token-act-pair · gemini-2.0-flash

    school grade levels

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

    school grades

    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
    
    -0.63
     ويكيميديا
    -0.59
     ***!
    -0.55
     doInBackground
    -0.55
     '/';
    -0.55
     Jefus
    -0.53
     Lov
    -0.51
     reafon
    -0.51
    Kilder
    -0.50
    OVERY
    -0.49
    POSITIVE LOGITS
     eighth
    1.26
     ninth
    1.20
     seventh
    1.16
     sixth
    1.00
    seventh
    0.96
     tenth
    0.94
    eighth
    0.94
     grade
    0.93
     Eighth
    0.93
     twelfth
    0.90
    Activations Density 1.966%

    No Known Activations