© 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. 13833
    Prev
    Next
    INDEX
    Explanations

    general words indicating positive sentiment, often related to personal experiences or connections

    oai_token-act-pair · gemini-2.0-flash

    actions and expressions of experience

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

    and

    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
     itſelf
    -0.79
     الحره
    -0.69
    InjectAttribute
    -0.69
     سكانية
    -0.69
     tartalomajánló
    -0.66
     EconPapers
    -0.66
     yonder
    -0.63
     الرياضيه
    -0.60
    Viited
    -0.58
    }$​
    -0.58
    POSITIVE LOGITS
     being
    0.61
     showing
    0.56
     that
    0.55
     getting
    0.52
     didn
    0.52
     saper
    0.52
     célèbres
    0.51
     taking
    0.51
     trying
    0.51
    sor
    0.50
    Activations Density 4.370%

    No Known Activations