© 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. 14371
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, especially 'I', as well as names and ages

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs

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

    Graduated/worked/attended

    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
    theim
    -0.49
    ArgumentParser
    -0.47
    Abitanti
    -0.46
    
    -0.43
    نم
    -0.43
    NOPQRST
    -0.41
     урна
    -0.41
    bcryptjs
    -0.40
    lamento
    -0.40
    bParam
    -0.40
    POSITIVE LOGITS
     attended
    0.87
     مشين
    0.83
     graduated
    0.79
     grew
    0.77
    Worked
    0.77
     worked
    0.76
    attended
    0.76
     Served
    0.75
     Worked
    0.75
     attends
    0.74
    Activations Density 4.244%

    No Known Activations