© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11173
    Prev
    Next
    INDEX
    Explanations

    opinions in political commentary

    oai_token-act-pair · gemini-2.0-flash

    Further text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    GEBURTS
    -0.64
    NewUrlParser
    -0.63
     MainAxisSize
    -0.57
    __':
    -0.56
    KommentareTeilen
    -0.54
     execute
    -0.52
    請繼續往下閱讀
    -0.52
    __":
    -0.51
    DrawerToggle
    -0.49
    )__
    -0.49
    POSITIVE LOGITS
     entrust
    0.61
     Roskov
    0.60
    最快更新
    0.59
    AddField
    0.57
     enshr
    0.56
    glfw
    0.55
    :✨
    0.53
    PutMapping
    0.53
    RemoveField
    0.52
     bypassing
    0.52
    Activations Density 2.401%

    No Known Activations