© 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. 15485
    Prev
    Next
    INDEX
    Explanations

    locations, specifically cities and countries

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
     myſelf
    -1.21
     themſelves
    -1.14
     itſelf
    -1.08
    ſelf
    -1.03
     pleaſure
    -1.02
     himſelf
    -1.02
     reaſon
    -1.00
     purpoſe
    -0.97
     poffible
    -0.96
     uſed
    -0.95
    POSITIVE LOGITS
    ,
    0.44
     c
    0.42
    p
    0.42
     rayos
    0.41
    C
    0.41
    P
    0.41
     frenos
    0.40
     orígenes
    0.40
     neumáticos
    0.40
    v
    0.40
    Activations Density 1.418%

    No Known Activations