© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5022
    Prev
    Next
    INDEX
    Explanations

    common short words (pronouns, articles, prepositions) in Spanish, French, and Portuguese, and sometimes English

    oai_token-act-pair · gemini-2.0-flash

    el

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ſeveral
    -1.10
     Monfieur
    -0.98
     Jefus
    -0.96
     grève
    -0.96
     itſelf
    -0.91
     Reſ
    -0.91
     Cæsar
    -0.90
     ſever
    -0.88
     houſe
    -0.88
     ſche
    -0.87
    POSITIVE LOGITS
     Far
    0.54
     su
    0.51
     far
    0.49
     cui
    0.46
     can
    0.45
     I
    0.44
     vis
    0.44
     cam
    0.43
     set
    0.43
     com
    0.43
    Activations Density 2.693%

    No Known Activations