© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11195
    Prev
    Next
    INDEX
    Explanations

    mentions of exceptions being caught in code, comparisons, exposure during experiments, job related wording, and quantum states in physics.

    oai_token-act-pair · gemini-2.0-flash

    French words

    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
     Ex
    -2.03
    Ex
    -1.96
     EX
    -1.92
     ex
    -1.91
    EX
    -1.78
    ex
    -1.76
     exp
    -1.75
     Exp
    -1.72
     exc
    -1.55
    Exp
    -1.55
    POSITIVE LOGITS
    automne
    0.49
    assemblée
    0.46
    humanité
    0.46
    enfance
    0.43
    autonomie
    0.41
    amitié
    0.40
     personalidade
    0.40
    océan
    0.39
     réguli
    0.38
     cará
    0.38
    Activations Density 1.430%

    No Known Activations