© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    references to the US government and political processes, especially regarding federal appointments

    oai_token-act-pair · gemini-2.0-flash

    Confirming nominations

    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
    SuppressMessage
    -0.58
    kloped
    -0.53
     Rubin
    -0.52
    İstinadlar
    -0.51
     rank
    -0.51
     trans
    -0.48
    Архівовано
    -0.47
    Parcelize
    -0.47
     chi̍t
    -0.45
    rank
    -0.44
    POSITIVE LOGITS
     Confirmed
    1.07
     confirmation
    1.06
     confirmed
    1.05
     Confirmation
    1.03
     confirm
    1.03
     confirming
    1.02
     confirms
    1.01
     Confirm
    0.97
    Confirmation
    0.96
     confirmations
    0.95
    Activations Density 3.662%

    No Known Activations