© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15684
    Prev
    Next
    INDEX
    Explanations

    terms related to the judicial system and attempts to influence outcomes.

    oai_token-act-pair · gemini-2.0-flash

    make

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     otomatig
    -0.70
     Offisielt
    -0.67
    Demografia
    -0.65
     Inti
    -0.65
    migrationBuilder
    -0.62
     NDEBUG
    -0.62
     ujednoznacz
    -0.61
    lihood
    -0.60
    protoimpl
    -0.59
     Ellos
    -0.58
    POSITIVE LOGITS
     '{@
    0.68
    urlpatterns
    0.63
    Lähteet
    0.62
     its
    0.61
    AutoScaleMode
    0.58
    ."—
    0.54
    ⁢
    0.54
     his
    0.54
     pungkasnya
    0.54
     the
    0.52
    Activations Density 0.991%

    No Known Activations