© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15539
    Prev
    Next
    INDEX
    Explanations

    exclamation points and words of surprise or pleasure, or mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    !

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     مشين
    -0.72
    initialise
    -0.70
     enquiry
    -0.67
    :-
    -0.67
     enquiries
    -0.65
     tyres
    -0.65
    లాలు
    -0.64
     démocratie
    -0.64
    cognised
    -0.64
    glClear
    -0.63
    POSITIVE LOGITS
     oftentimes
    0.61
    Ehh
    0.53
     soudain
    0.53
     nvm
    0.51
     smer
    0.50
    Uhh
    0.49
    FUCK
    0.49
     hallway
    0.49
    Welp
    0.48
     manor
    0.47
    Activations Density 3.144%

    No Known Activations