© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16273
    Prev
    Next
    INDEX
    Explanations

    capitalized words or phrases that appear to be proper nouns or titles and numbers

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns/Named entities

    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
     picioare
    -0.41
     '`
    -0.39
     Basta
    -0.39
     hende
    -0.39
     alike
    -0.38
     sauvage
    -0.36
     Espero
    -0.35
     vuestro
    -0.35
     mec
    -0.34
    .*/
    -0.34
    POSITIVE LOGITS
     autorytatywna
    1.02
    مصادر
    1.02
    Hentet
    0.98
     lenker
    0.93
    таратура
    0.87
    Референце
    0.85
     חיצוניים
    0.84
    Искәрмәләр
    0.82
    adaptiveStyles
    0.81
     unknownFields
    0.80
    Activations Density 11.207%

    No Known Activations