© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16061
    Prev
    Next
    INDEX
    Explanations

    names of places, especially ancient places and regions

    oai_token-act-pair · gemini-2.0-flash

    Places and historical context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    -1.13
     myſelf
    -1.12
     Monfieur
    -1.05
     faſt
    -1.04
     ſmall
    -1.02
     itſelf
    -1.01
     purpoſe
    -1.00
     pleaſure
    -1.00
     Anſ
    -0.99
     houſe
    -0.99
    POSITIVE LOGITS
     he
    0.50
    im
    0.49
     C
    0.48
     Be
    0.47
     Kam
    0.47
    TagHelper
    0.47
     b
    0.47
     or
    0.46
     major
    0.45
     R
    0.44
    Activations Density 0.801%

    No Known Activations