© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3040
    Prev
    Next
    INDEX
    Explanations

    the phrase "it comes as no surprise" and words that suggest shock or tension

    oai_token-act-pair · gemini-2.0-flash

    come

    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
    findpost
    -0.68
     getItemCount
    -0.67
    INCREF
    -0.60
     Efq
    -0.60
     internetowa
    -0.59
    agrid
    -0.58
    createComponent
    -0.57
    /**
    -0.53
    +#+#
    -0.53
     AssemblyProduct
    -0.53
    POSITIVE LOGITS
     come
    1.76
     comes
    1.64
     Come
    1.43
    come
    1.43
     came
    1.41
    comes
    1.41
     COME
    1.40
     COMES
    1.39
     Comes
    1.38
    Come
    1.36
    Activations Density 1.572%

    No Known Activations