© 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. 14042
    Prev
    Next
    INDEX
    Explanations

    terms related to government or military organization or leadership

    oai_token-act-pair · gemini-2.0-flash

    titles or positions

    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
     caucus
    -0.46
     senator
    -0.46
    int
    -0.45
    議員
    -0.45
    BlockPos
    -0.45
    akses
    -0.44
    tagext
    -0.44
     distrito
    -0.44
     Familienname
    -0.43
    لی
    -0.42
    POSITIVE LOGITS
     surla
    0.75
    tvguidetime
    0.68
    pushFollow
    0.66
    setopt
    0.63
     архивлан
    0.60
    pherds
    0.59
    ẨM
    0.59
    AxisAlignment
    0.59
     cherchés
    0.57
    ISODE
    0.57
    Activations Density 1.611%

    No Known Activations