© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4607
    Prev
    Next
    INDEX
    Explanations

    exclamation marks and related punctuation or words

    oai_token-act-pair · gemini-2.0-flash

    exclamation points

    np_max-act · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
    !
    -2.67
    !
    -2.45
    !</
    -2.28
    !}
    -2.25
    !’
    -2.17
    !]
    -2.17
    !»
    -2.14
    !')
    -2.11
    !”
    -2.06
    !")
    -2.06
    POSITIVE LOGITS
    ↵↵
    0.93
     The
    0.85
     
    0.84
     “
    0.79
     "
    0.77
     In
    0.73
     (
    0.70
     in
    0.69
     $
    0.68
     To
    0.68
    Activations Density 0.749%

    No Known Activations