© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12212
    Prev
    Next
    INDEX
    Explanations

    references to deities and battles between them

    oai_token-act-pair · gemini-2.0-flash

    Mythology and storytelling

    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
    TOC
    -0.51
    FO
    -0.44
    orgung
    -0.43
    ля
    -0.42
    tc
    -0.41
    டம்
    -0.41
     First
    -0.40
    TC
    -0.40
    iloc
    -0.40
     Guill
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.93
     Roskov
    0.82
     فريبيس
    0.76
     linkovi
    0.75
    StoryboardSegue
    0.70
    
    0.69
     ResultSet
    0.68
    featureID
    0.68
     препратки
    0.67
     INTERESAR
    0.66
    Activations Density 7.859%

    No Known Activations