© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13265
    Prev
    Next
    INDEX
    Explanations

    uses of the word "you" and the phrase "hard to believe" or the contraction "couldn't"

    oai_token-act-pair · gemini-2.0-flash

    believe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     <<<<<<<<<<<<<<
    -0.57
    /**
    -0.54
    Билгалдахарш
    -0.52
     BorderSide
    -0.48
    cstdlib
    -0.48
    Viitteet
    -0.47
    culaires
    -0.47
    httphttps
    -0.47
    مصادر
    -0.46
     يتيمه
    -0.46
    POSITIVE LOGITS
     believe
    1.84
    believe
    1.69
     Believe
    1.63
     BELIEVE
    1.61
     belief
    1.61
    Believe
    1.54
     Belief
    1.52
     believing
    1.51
     believes
    1.45
    belief
    1.45
    Activations Density 1.496%

    No Known Activations