© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14168
    Prev
    Next
    INDEX
    Explanations

    the word "tip"

    oai_token-act-pair · gemini-2.0-flash

    tip

    np_max-act · gemini-2.0-flash

    tip

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -1.06
     
    -0.81
     very
    -0.75
     two
    -0.69
     common
    -0.68
     new
    -0.68
     three
    -0.66
     key
    -0.65
    s
    -0.65
     one
    -0.64
    POSITIVE LOGITS
     démission
    1.23
     anún
    1.22
     vérit
    1.16
     étoient
    1.16
     feroit
    1.14
     pouvoit
    1.14
     définiti
    1.13
     avoient
    1.13
     bonté
    1.12
     fidélité
    1.10
    Activations Density 1.760%

    No Known Activations