© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13472
    Prev
    Next
    INDEX
    Explanations

    text describing military honors and decorated soldiers.

    oai_token-act-pair · gemini-2.0-flash

    unrecognized or non-English tokens

    np_token-act-pair-logits · gpt-4o-mini

    military and government personnel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Lieutenant
    -1.09
     sergeant
    -0.98
     lieutenant
    -0.97
     Lt
    -0.97
     Sergeant
    -0.96
    Lt
    -0.91
     Corporal
    -0.89
    Lieutenant
    -0.89
     officers
    -0.87
     officer
    -0.87
    POSITIVE LOGITS
     Meksiku
    0.61
     estekak
    0.57
     Reverso
    0.54
    Билгалдахарш
    0.52
    mrb
    0.51
     MainAxisSize
    0.51
    EndContext
    0.51
     wyg
    0.50
    enumi
    0.49
    Orsay
    0.47
    Activations Density 0.565%

    No Known Activations