© 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. 12729
    Prev
    Next
    INDEX
    Explanations

    information about military history, especially promotions and groups of people

    oai_token-act-pair · gemini-2.0-flash

    military ranks

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

    military ranks

    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
     Meksiku
    -0.65
     Wikimedijinoj
    -0.65
     utafitiHapana
    -0.59
    PreferredItem
    -0.59
    GOTREF
    -0.58
     calendriers
    -0.58
    InitVars
    -0.57
    taxia
    -0.56
     dévelo
    -0.54
    abestanden
    -0.54
    POSITIVE LOGITS
     Lieutenant
    1.45
     Captain
    1.35
     Lt
    1.34
     Major
    1.33
    Lieutenant
    1.28
     lieutenant
    1.26
     Sergeant
    1.26
    Lt
    1.23
     Capt
    1.20
    Major
    1.20
    Activations Density 2.876%

    No Known Activations